https://varunvemulapalli.com/ 2026-10-29 1.0 https://varunvemulapalli.com/blog/ 2027-01-09 0.9 https://varunvemulapalli.com/claude-certifications.html 2026-10-29 0.8 https://varunvemulapalli.com/ai-consultant-dallas-fort-worth.html 2026-10-29 0.9 https://varunvemulapalli.com/claude-certified-ai-consultant.html 2026-10-29 0.9 https://varunvemulapalli.com/forward-deployed-ai-engineer.html 2026-10-29 0.9 https://varunvemulapalli.com/blog/day-01.html 2026-10-02 0.8 https://varunvemulapalli.com/blog/day-01-what-is-ai/poster.jpgDay 1: What is AI?AI is software that learns patterns from examples so it can recognize, predict or decide on situations it hasn't seen before.https://varunvemulapalli.com/blog/day-01-what-is-ai/explainer.mp4130 https://varunvemulapalli.com/blog/day-02.html 2026-10-03 0.8 https://varunvemulapalli.com/blog/day-02-ai-vs-machine-learning-vs-deep-learning/poster.jpgDay 2: AI vs machine learning vs deep learning vs generative AIAI is the umbrella, Machine Learning learns from examples, Deep Learning does it with many-layered neural networks, and Generative AI uses that to…https://varunvemulapalli.com/blog/day-02-ai-vs-machine-learning-vs-deep-learning/explainer.mp4130 https://varunvemulapalli.com/blog/day-03.html 2026-10-04 0.8 https://varunvemulapalli.com/blog/day-03-how-machines-learn-from-examples/poster.jpgDay 3: How machines learn from examplesA machine "learns" by guessing, measuring how wrong it was on examples with known answers, and adjusting, over and over, until its guesses get good.https://varunvemulapalli.com/blog/day-03-how-machines-learn-from-examples/explainer.mp4126 https://varunvemulapalli.com/blog/day-04.html 2026-10-05 0.8 https://varunvemulapalli.com/blog/day-04-data-features-and-labels/poster.jpgDay 4: Data, features and labelsData is the past examples, features are the clues, labels are the answers, and a model is only as good as all three.https://varunvemulapalli.com/blog/day-04-data-features-and-labels/explainer.mp4101 https://varunvemulapalli.com/blog/day-05.html 2026-10-06 0.8 https://varunvemulapalli.com/blog/day-05-training-vs-inference/poster.jpgDay 5: Training vs inferenceTraining is the slow, expensive learning done ahead of time; inference is the fast answer the frozen model gives every time you use it.https://varunvemulapalli.com/blog/day-05-training-vs-inference/explainer.mp4104 https://varunvemulapalli.com/blog/day-06.html 2026-10-07 0.8 https://varunvemulapalli.com/blog/day-06-supervised-unsupervised-and-reinforcement-learning/poster.jpgDay 6: Supervised, unsupervised and reinforcement learningSupervised learns from answers, unsupervised finds patterns without answers, and reinforcement learns from rewards for its own actions.https://varunvemulapalli.com/blog/day-06-supervised-unsupervised-and-reinforcement-learning/explainer.mp4127 https://varunvemulapalli.com/blog/day-07.html 2026-10-08 0.8 https://varunvemulapalli.com/blog/day-07-accuracy-precision-and-recall/poster.jpgDay 7: Accuracy, precision and recallAccuracy says how often a model is right overall; precision says how much to trust its alarms; recall says how many real problems it catches.https://varunvemulapalli.com/blog/day-07-accuracy-precision-and-recall/explainer.mp4113 https://varunvemulapalli.com/blog/day-08.html 2026-10-09 0.8 https://varunvemulapalli.com/blog/day-08-overfitting/poster.jpgDay 8: OverfittingOverfitting is when a model memorizes its training data instead of learning the pattern, so it looks great in practice and fails on anything new.https://varunvemulapalli.com/blog/day-08-overfitting/explainer.mp4108 https://varunvemulapalli.com/blog/day-09.html 2026-10-10 0.8 https://varunvemulapalli.com/blog/day-09-neurons-and-neural-networks/poster.jpgDay 9: Neurons and neural networksA neuron multiplies inputs by learned weights, adds them up and decides; stack enough of them in layers and you get a neural network.https://varunvemulapalli.com/blog/day-09-neurons-and-neural-networks/explainer.mp4107 https://varunvemulapalli.com/blog/day-10.html 2026-10-11 0.8 https://varunvemulapalli.com/blog/day-10-loss-gradient-descent-and-backpropagation/poster.jpgDay 10: Loss, gradient descent and backpropagationA network learns by measuring how wrong it is (loss), working out each weights share of the blame (backpropagation) and nudging every weight downhill…https://varunvemulapalli.com/blog/day-10-loss-gradient-descent-and-backpropagation/explainer.mp4104 https://varunvemulapalli.com/blog/day-11.html 2026-10-12 0.8 https://varunvemulapalli.com/blog/day-11-embeddings/poster.jpgDay 11: EmbeddingsAn embedding turns meaning into a list of numbers, so similar things land close together and AI can measure similarity with simple math.https://varunvemulapalli.com/blog/day-11-embeddings/explainer.mp4112 https://varunvemulapalli.com/blog/day-12.html 2026-10-13 0.8 https://varunvemulapalli.com/blog/day-12-how-ai-sees-images/poster.jpgDay 12: How AI sees imagesAI sees an image as a grid of numbers and builds up from edges to shapes to objects, layer by layer, using filters it learned from labeled examples.https://varunvemulapalli.com/blog/day-12-how-ai-sees-images/explainer.mp4120 https://varunvemulapalli.com/blog/day-13.html 2026-10-14 0.8 https://varunvemulapalli.com/blog/day-13-transfer-learning-and-gpus/poster.jpgDay 13: Transfer learning and GPUsTransfer learning reuses what a big model already learned so you need far less data, and GPUs make the heavy number-crunching fast by doing it in parallel.https://varunvemulapalli.com/blog/day-13-transfer-learning-and-gpus/explainer.mp4111 https://varunvemulapalli.com/blog/day-14.html 2026-10-15 0.8 https://varunvemulapalli.com/blog/day-14-recap-and-quiz-days-1-13/poster.jpgDay 14: Recap and quiz: Days 1–13Two weeks in. If you've followed along, you now understand more about how AI works than many people who use it every day.https://varunvemulapalli.com/blog/day-14-recap-and-quiz-days-1-13/explainer.mp4116 https://varunvemulapalli.com/blog/day-15.html 2026-10-16 0.8 https://varunvemulapalli.com/blog/day-15-what-is-generative-ai/poster.jpgDay 15: What is generative AI?Classic AI picks from options it was given, while generative AI creates new content by predicting the next word, over and over.https://varunvemulapalli.com/blog/day-15-what-is-generative-ai/explainer.mp4106 https://varunvemulapalli.com/blog/day-16.html 2026-10-17 0.8 https://varunvemulapalli.com/blog/day-16-tokens/poster.jpgDay 16: TokensLLMs read text as tokens (about ¾ of a word each in English), and tokens drive both your bill and your limits.https://varunvemulapalli.com/blog/day-16-tokens/explainer.mp4116 https://varunvemulapalli.com/blog/day-17.html 2026-10-18 0.8 https://varunvemulapalli.com/blog/day-17-transformers-and-attention/poster.jpgDay 17: Transformers and attentionTransformers use attention so every word can look at every other word at once, which is how AI understands words in context.https://varunvemulapalli.com/blog/day-17-transformers-and-attention/explainer.mp4100 https://varunvemulapalli.com/blog/day-18.html 2026-10-19 0.8 https://varunvemulapalli.com/blog/day-18-how-llms-are-pretrained/poster.jpgDay 18: How LLMs are pretrainedPretraining teaches a model language, facts and patterns through billions of next-word guesses, but it stops at a cutoff date and isn't an assistant yet.https://varunvemulapalli.com/blog/day-18-how-llms-are-pretrained/explainer.mp4109 https://varunvemulapalli.com/blog/day-19.html 2026-10-20 0.8 https://varunvemulapalli.com/blog/day-19-fine-tuning-and-rlhf/poster.jpgDay 19: Fine-tuning and RLHFFine-tuning teaches a model your format from approved examples, and RLHF teaches it what people prefer by learning from their choices between answers.https://varunvemulapalli.com/blog/day-19-fine-tuning-and-rlhf/explainer.mp4111 https://varunvemulapalli.com/blog/day-20.html 2026-10-21 0.8 https://varunvemulapalli.com/blog/day-20-context-windows/poster.jpgDay 20: Context windowsThe context window is the model's working memory in tokens; when you overfill it, things get cut or ignored, so send only what matters.https://varunvemulapalli.com/blog/day-20-context-windows/explainer.mp4110 https://varunvemulapalli.com/blog/day-21.html 2026-10-22 0.8 https://varunvemulapalli.com/blog/day-21-temperature-and-sampling/poster.jpgDay 21: Temperature and samplingTemperature decides how adventurous the model is when picking each next word: turn it up for ideas, down for answers that must stay consistent.https://varunvemulapalli.com/blog/day-21-temperature-and-sampling/explainer.mp4111 https://varunvemulapalli.com/blog/day-22.html 2026-10-23 0.8 https://varunvemulapalli.com/blog/day-22-hallucinations/poster.jpgDay 22: HallucinationsLLMs predict plausible text rather than look things up, so give them the source, ask them to cite it, let them say "I don't know", and verify anything…https://varunvemulapalli.com/blog/day-22-hallucinations/explainer.mp4118 https://varunvemulapalli.com/blog/day-23.html 2026-10-24 0.8 https://varunvemulapalli.com/blog/day-23-prompt-engineering-basics/poster.jpgDay 23: Prompt engineering basicsGive the model a role, a clear task, the context, the format you want and the rules to follow, and a vague answer becomes a usable one.https://varunvemulapalli.com/blog/day-23-prompt-engineering-basics/explainer.mp487 https://varunvemulapalli.com/blog/day-24.html 2026-10-25 0.8 https://varunvemulapalli.com/blog/day-24-few-shot-prompting-and-step-by-step/poster.jpgDay 24: Few-shot prompting and step-by-step reasoningShow the model a few labeled examples to get consistent answers in your format, and ask it to reason step by step when the task has math or multiple steps.https://varunvemulapalli.com/blog/day-24-few-shot-prompting-and-step-by-step/explainer.mp4113 https://varunvemulapalli.com/blog/day-25.html 2026-10-26 0.8 https://varunvemulapalli.com/blog/day-25-system-prompts-and-roles/poster.jpgDay 25: System prompts and rolesThe system prompt sets who the assistant is and the rules it follows, the user message is the request, and the assistant reply should follow both, with…https://varunvemulapalli.com/blog/day-25-system-prompts-and-roles/explainer.mp496 https://varunvemulapalli.com/blog/day-26.html 2026-10-27 0.8 https://varunvemulapalli.com/blog/day-26-structured-outputs-json/poster.jpgDay 26: Structured outputs: JSONDefine a schema, ask the model for JSON that matches it, and validate every result, so AI output can flow into real systems instead of being copied by…https://varunvemulapalli.com/blog/day-26-structured-outputs-json/explainer.mp497 https://varunvemulapalli.com/blog/day-27.html 2026-10-28 0.8 https://varunvemulapalli.com/blog/day-27-multimodal-ai/poster.jpgDay 27: Multimodal AIMultimodal AI reads images, audio and text together, which makes intake faster and richer, but a human still checks what the model thinks it sees.https://varunvemulapalli.com/blog/day-27-multimodal-ai/explainer.mp4108 https://varunvemulapalli.com/blog/day-28.html 2026-10-29 0.8 https://varunvemulapalli.com/blog/day-28-recap-of-days-15-27/poster.jpgDay 28: Recap of Days 15–27An LLM predicts the next token from patterns; clear prompts, real sources and structured output make it reliable at work.https://varunvemulapalli.com/blog/day-28-recap-of-days-15-27/explainer.mp4109 https://varunvemulapalli.com/blog/day-29.html 2026-10-30 0.8 https://varunvemulapalli.com/blog/day-29-semantic-search/poster.jpgDay 29: Semantic searchSemantic search compares meanings as embeddings, so it finds the right answer even when the user's words don't match the document's.https://varunvemulapalli.com/blog/day-29-semantic-search/explainer.mp495 https://varunvemulapalli.com/blog/day-30.html 2026-10-31 0.8 https://varunvemulapalli.com/blog/day-30-vector-databases/poster.jpgDay 30: Vector databasesA vector database stores embeddings with their metadata and quickly finds the closest matches by meaning, which is what makes semantic search work at…https://varunvemulapalli.com/blog/day-30-vector-databases/explainer.mp4101 https://varunvemulapalli.com/blog/day-31.html 2026-11-01 0.8 https://varunvemulapalli.com/blog/day-31-retrieval-augmented-generation-rag/poster.jpgDay 31: Retrieval-augmented generation (RAG)RAG retrieves the right passages from your own documents and gives them to the model, so answers are grounded, current and traceable to a source.https://varunvemulapalli.com/blog/day-31-retrieval-augmented-generation-rag/explainer.mp4134 https://varunvemulapalli.com/blog/day-32.html 2026-11-02 0.8 https://varunvemulapalli.com/blog/day-32-chunking-and-retrieval-quality/poster.jpgDay 32: Chunking and retrieval qualityGood RAG starts with good chunks: split by structure, keep tables whole, add overlap and metadata, and test retrieval with real questions.https://varunvemulapalli.com/blog/day-32-chunking-and-retrieval-quality/explainer.mp4118 https://varunvemulapalli.com/blog/day-33.html 2026-11-03 0.8 https://varunvemulapalli.com/blog/day-33-open-vs-closed-models-and-how-to/poster.jpgDay 33: Open vs closed models, and how to choose oneOpen-weight models give you control but you run them; closed models give you ease but you trust a provider, so test both on your own task, cost and…https://varunvemulapalli.com/blog/day-33-open-vs-closed-models-and-how-to/explainer.mp4107 https://varunvemulapalli.com/blog/day-34.html 2026-11-04 0.8 https://varunvemulapalli.com/blog/day-34-recap-of-days-29-33/poster.jpgDay 34: Recap of Days 29–33Phase 4 done. You now know how to give an AI model knowledge it was never trained on, and how to pick the model in the first place.https://varunvemulapalli.com/blog/day-34-recap-of-days-29-33/explainer.mp483 https://varunvemulapalli.com/blog/day-35.html 2026-11-05 0.8 https://varunvemulapalli.com/blog/day-35-chatbot-vs-workflow-vs-agent/poster.jpgDay 35: Chatbot vs workflow vs agentUse a chatbot to answer, a workflow when the steps are known, and an agent only when the steps depend on what it discovers along the way.https://varunvemulapalli.com/blog/day-35-chatbot-vs-workflow-vs-agent/explainer.mp4113 https://varunvemulapalli.com/blog/day-36.html 2026-11-06 0.8 https://varunvemulapalli.com/blog/day-36-the-agent-loop/poster.jpgDay 36: The agent loopAn agent is a loop of think, act, observe, repeat, and the stopping conditions you give it matter as much as the goal.https://varunvemulapalli.com/blog/day-36-the-agent-loop/explainer.mp4104 https://varunvemulapalli.com/blog/day-37.html 2026-11-07 0.8 https://varunvemulapalli.com/blog/day-37-tool-use-function-calling/poster.jpgDay 37: Tool use / function callingWith tool use, the model decides which function to call and with what inputs, and your app runs it and returns the result, so answers come from real…https://varunvemulapalli.com/blog/day-37-tool-use-function-calling/explainer.mp4111 https://varunvemulapalli.com/blog/day-38.html 2026-11-08 0.8 https://varunvemulapalli.com/blog/day-38-designing-good-tools-for-an-agent/poster.jpgDay 38: Designing good tools for an agentGive an agent small, clearly named tools with typed inputs, helpful errors and only the access each job needs, and it will guess less and break less.https://varunvemulapalli.com/blog/day-38-designing-good-tools-for-an-agent/explainer.mp4108 https://varunvemulapalli.com/blog/day-39.html 2026-11-09 0.8 https://varunvemulapalli.com/blog/day-39-memory-and-state/poster.jpgDay 39: Memory and stateModels don't remember; apps give agents memory by saving the right facts and task state and feeding them back in, and deciding what not to store…https://varunvemulapalli.com/blog/day-39-memory-and-state/explainer.mp4112 https://varunvemulapalli.com/blog/day-40.html 2026-11-10 0.8 https://varunvemulapalli.com/blog/day-40-planning-and-multi-step-tasks/poster.jpgDay 40: Planning and multi-step tasksGood agents break a goal into ordered steps, respect what depends on what, and re-plan out loud when something goes missing.https://varunvemulapalli.com/blog/day-40-planning-and-multi-step-tasks/explainer.mp499 https://varunvemulapalli.com/blog/day-41.html 2026-11-11 0.8 https://varunvemulapalli.com/blog/day-41-mcp-model-context-protocol/poster.jpgDay 41: MCP (Model Context Protocol)MCP is a shared standard that lets any compatible AI app plug into tools and data through servers, so you build each connection once, not once per app.https://varunvemulapalli.com/blog/day-41-mcp-model-context-protocol/explainer.mp4118 https://varunvemulapalli.com/blog/day-42.html 2026-11-12 0.8 https://varunvemulapalli.com/blog/day-42-agent-patterns/poster.jpgDay 42: Agent patternsChaining, routing, parallel and orchestrator–workers are building blocks; pick the simplest one that fits the work.https://varunvemulapalli.com/blog/day-42-agent-patterns/explainer.mp4126 https://varunvemulapalli.com/blog/day-43.html 2026-11-13 0.8 https://varunvemulapalli.com/blog/day-43-multi-agent-systems-and-subagents/poster.jpgDay 43: Multi-agent systems and subagentsMulti-agent systems give each part of a big job its own clean context, which helps on wide research but adds cost, so use them only when the work truly…https://varunvemulapalli.com/blog/day-43-multi-agent-systems-and-subagents/explainer.mp4122 https://varunvemulapalli.com/blog/day-44.html 2026-11-14 0.8 https://varunvemulapalli.com/blog/day-44-human-in-the-loop/poster.jpgDay 44: Human-in-the-loopHuman-in-the-loop lets agents handle routine cases on their own and pause for a person on high-stakes ones, with every decision logged.https://varunvemulapalli.com/blog/day-44-human-in-the-loop/explainer.mp4117 https://varunvemulapalli.com/blog/day-45.html 2026-11-15 0.8 https://varunvemulapalli.com/blog/day-45-guardrails-and-prompt-injection/poster.jpgDay 45: Guardrails and prompt injectionAnything an AI reads can try to give it orders, so treat content as data, check inputs and outputs, limit what the AI can do, and keep a human on…https://varunvemulapalli.com/blog/day-45-guardrails-and-prompt-injection/explainer.mp4112 https://varunvemulapalli.com/blog/day-46.html 2026-11-16 0.8 https://varunvemulapalli.com/blog/day-46-recap-of-days-35-45-which-tool/poster.jpgDay 46: Recap of Days 35–45 + which tool for which jobAgents think, act and observe with tools, under guardrails and human checkpoints. From tomorrow, we build.https://varunvemulapalli.com/blog/day-46-recap-of-days-35-45-which-tool/explainer.mp496 https://varunvemulapalli.com/blog/day-47.html 2026-11-17 0.8 https://varunvemulapalli.com/blog/day-47-your-setup-vs-code-and-the-terminal/poster.jpgDay 47: Your setup: VS Code and the terminalThe terminal is a precise text conversation with your computer, and five safe commands are enough to find your way around and set up your workspace.https://varunvemulapalli.com/blog/day-47-your-setup-vs-code-and-the-terminal/explainer.mp4108 https://varunvemulapalli.com/blog/day-48.html 2026-11-18 0.8 https://varunvemulapalli.com/blog/day-48-git-and-github-basics/poster.jpgDay 48: Git and GitHub basicsCommits are save points, branches are safe copies, and pull requests are reviewed merges, so a team (or an AI agent) can change shared files without chaos.https://varunvemulapalli.com/blog/day-48-git-and-github-basics/explainer.mp4110 https://varunvemulapalli.com/blog/day-49.html 2026-11-19 0.8 https://varunvemulapalli.com/blog/day-49-python-essentials-for-building-agents/poster.jpgDay 49: Python essentials for building agentsVariables, lists, dicts, loops, functions and packages are enough to read data and build the small tools agents rely on.https://varunvemulapalli.com/blog/day-49-python-essentials-for-building-agents/explainer.mp4101 https://varunvemulapalli.com/blog/day-50.html 2026-11-20 0.8 https://varunvemulapalli.com/blog/day-50-apis-and-json-explained/poster.jpgDay 50: APIs and JSON explainedAn API is a waiter between programs: you send a request to a URL with a method, and get back a status code and a JSON body you can read key by key.https://varunvemulapalli.com/blog/day-50-apis-and-json-explained/explainer.mp4108 https://varunvemulapalli.com/blog/day-51.html 2026-11-21 0.8 https://varunvemulapalli.com/blog/day-51-api-keys-environment-variables-and-keeping-secrets/poster.jpgDay 51: API keys, environment variables and keeping secrets safeKeep keys in environment variables, keep .env out of Git, and if a key leaks, revoke it first and clean up second.https://varunvemulapalli.com/blog/day-51-api-keys-environment-variables-and-keeping-secrets/explainer.mp4124 https://varunvemulapalli.com/blog/day-52.html 2026-11-22 0.8 https://varunvemulapalli.com/blog/day-52-how-to-read-developer-docs-quickly/poster.jpgDay 52: How to read developer docs quicklyRead docs on a fixed path (quickstart, auth, one endpoint, errors, rate limits) and skip the rest until you need it.https://varunvemulapalli.com/blog/day-52-how-to-read-developer-docs-quickly/explainer.mp4104 https://varunvemulapalli.com/blog/day-53.html 2026-11-23 0.8 https://varunvemulapalli.com/blog/day-53-your-first-api-call-to-an-llm/poster.jpgDay 53: Your first API call to an LLMAn LLM API call is a POST with a model and a prompt; ask for JSON and the answer can feed your code.https://varunvemulapalli.com/blog/day-53-your-first-api-call-to-an-llm/explainer.mp4109 https://varunvemulapalli.com/blog/day-54.html 2026-11-24 0.8 https://varunvemulapalli.com/blog/day-54-recap-of-days-47-53/poster.jpgDay 54: Recap of Days 47–53Terminal, Git, Python, APIs, secrets, docs and one LLM call make up the builder's loop that coding agents will now run with you.https://varunvemulapalli.com/blog/day-54-recap-of-days-47-53/explainer.mp4114 https://varunvemulapalli.com/blog/day-55.html 2026-11-25 0.8 https://varunvemulapalli.com/blog/day-55-what-github-copilot-is-plans-and-setup/poster.jpgDay 55: What GitHub Copilot is, plans and setup in VS CodeGitHub Copilot is an AI assistant in your editor, and the free plan plus VS Code is all you need to start.https://varunvemulapalli.com/blog/day-55-what-github-copilot-is-plans-and-setup/explainer.mp4119 https://varunvemulapalli.com/blog/day-56.html 2026-11-26 0.8 https://varunvemulapalli.com/blog/day-56-code-completions-and-copilot-chat/poster.jpgDay 56: Code completions and Copilot ChatCompletions finish the line you're writing; Chat explains, questions and tests it, and you check both.https://varunvemulapalli.com/blog/day-56-code-completions-and-copilot-chat/explainer.mp4106 https://varunvemulapalli.com/blog/day-57.html 2026-11-27 0.8 https://varunvemulapalli.com/blog/day-57-agent-mode-in-vs-code-copilot-editing/poster.jpgDay 57: Agent mode in VS Code: Copilot editing across filesIn Agent, Copilot plans and edits across files, and your job becomes clear criteria and careful review.https://varunvemulapalli.com/blog/day-57-agent-mode-in-vs-code-copilot-editing/explainer.mp4106 https://varunvemulapalli.com/blog/day-58.html 2026-11-28 0.8 https://varunvemulapalli.com/blog/day-58-copilot-coding-agent-assign-an-issue-get/poster.jpgDay 58: Copilot coding agent: assign an issue, get a pull requestAssign a clear issue to Copilot cloud agent and it returns a pull request, but a human still reviews and merges.https://varunvemulapalli.com/blog/day-58-copilot-coding-agent-assign-an-issue-get/explainer.mp4107 https://varunvemulapalli.com/blog/day-59.html 2026-11-29 0.8 https://varunvemulapalli.com/blog/day-59-custom-instructions-and-mcp-servers-in-copilot/poster.jpgDay 59: Custom instructions and MCP servers in CopilotAn instructions file tells Copilot your project's rules, and MCP servers give it new tools.https://varunvemulapalli.com/blog/day-59-custom-instructions-and-mcp-servers-in-copilot/explainer.mp4103 https://varunvemulapalli.com/blog/day-60.html 2026-11-30 0.8 https://varunvemulapalli.com/blog/day-60-hands-on-build-a-small-working-tool/poster.jpgDay 60: Hands-on: build a small working tool with GitHub CopilotClear rules, worked numbers and tests turn Copilot into a reliable builder, and you into the checker.https://varunvemulapalli.com/blog/day-60-hands-on-build-a-small-working-tool/explainer.mp4116 https://varunvemulapalli.com/blog/day-61.html 2026-12-01 0.8 https://varunvemulapalli.com/blog/day-61-what-codex-is-cli-ide-and-cloud/poster.jpgDay 61: What Codex is: CLI, IDE and cloud agentCodex is one coding agent you can use from the terminal, your editor, the ChatGPT app or the cloud, and a safe first job is asking it to explain code…https://varunvemulapalli.com/blog/day-61-what-codex-is-cli-ide-and-cloud/explainer.mp4120 https://varunvemulapalli.com/blog/day-62.html 2026-12-02 0.8 https://varunvemulapalli.com/blog/day-62-setting-up-codex-and-your-first-task/poster.jpgDay 62: Setting up Codex and your first taskInstall Codex, sign in with ChatGPT, commit a checkpoint, and start with one failing test you can verify yourself.https://varunvemulapalli.com/blog/day-62-setting-up-codex-and-your-first-task/explainer.mp4105 https://varunvemulapalli.com/blog/day-63.html 2026-12-03 0.8 https://varunvemulapalli.com/blog/day-63-guiding-codex-with-agents-md/poster.jpgDay 63: Guiding Codex with AGENTS.mdAGENTS.md is the onboarding note for your coding agent: short, specific rules in the repo, loaded before every task.https://varunvemulapalli.com/blog/day-63-guiding-codex-with-agents-md/explainer.mp4109 https://varunvemulapalli.com/blog/day-64.html 2026-12-04 0.8 https://varunvemulapalli.com/blog/day-64-codex-for-tests-refactoring-and-code-review/poster.jpgDay 64: Codex for tests, refactoring and code reviewHave Codex write tests first, refactor second and review third, and keep a human as the final approver.https://varunvemulapalli.com/blog/day-64-codex-for-tests-refactoring-and-code-review/explainer.mp495 https://varunvemulapalli.com/blog/day-65.html 2026-12-05 0.8 https://varunvemulapalli.com/blog/day-65-hands-on-have-codex-build-and-test/poster.jpgDay 65: Hands-on: have Codex build and test a featureYou write the spec and the tricky example; Codex plans, builds, tests and reviews; you approve the commit.https://varunvemulapalli.com/blog/day-65-hands-on-have-codex-build-and-test/explainer.mp4109 https://varunvemulapalli.com/blog/day-66.html 2026-12-06 0.8 https://varunvemulapalli.com/blog/day-66-claude-for-builders-models-projects-and-artifacts/poster.jpgDay 66: Claude for builders: models, Projects and artifactsPick a model for the job, put the context in a Project once, and let artifacts turn chats into things you can click, share and reuse.https://varunvemulapalli.com/blog/day-66-claude-for-builders-models-projects-and-artifacts/explainer.mp4105 https://varunvemulapalli.com/blog/day-67.html 2026-12-07 0.8 https://varunvemulapalli.com/blog/day-67-your-first-claude-api-call/poster.jpgDay 67: Your first Claude API callA Claude API call is a model, a length limit and your messages, sent with a secret key, turning raw text into next steps from your own code.https://varunvemulapalli.com/blog/day-67-your-first-claude-api-call/explainer.mp4102 https://varunvemulapalli.com/blog/day-68.html 2026-12-08 0.8 https://varunvemulapalli.com/blog/day-68-tool-use-with-the-claude-api/poster.jpgDay 68: Tool use with the Claude APIWith tool use, Claude asks for a function call in JSON, your code runs it and returns a matching tool_result, and the answer is grounded in real data.https://varunvemulapalli.com/blog/day-68-tool-use-with-the-claude-api/explainer.mp4102 https://varunvemulapalli.com/blog/day-69.html 2026-12-09 0.8 https://varunvemulapalli.com/blog/day-69-claude-code-setup-and-your-first-session/poster.jpgDay 69: Claude Code: setup and your first sessionClaude Code is an agent in your terminal or editor that reads, runs and edits your project; give it clear expected-vs-actual and review every change.https://varunvemulapalli.com/blog/day-69-claude-code-setup-and-your-first-session/explainer.mp4111 https://varunvemulapalli.com/blog/day-70.html 2026-12-10 0.8 https://varunvemulapalli.com/blog/day-70-steering-claude-code-claude-md-slash-commands/poster.jpgDay 70: Steering Claude Code: CLAUDE.md, slash commands and skillsCLAUDE.md holds what Claude should always know, slash commands steer a session, and skills package a repeatable job your whole team can run by name.https://varunvemulapalli.com/blog/day-70-steering-claude-code-claude-md-slash-commands/explainer.mp498 https://varunvemulapalli.com/blog/day-71.html 2026-12-11 0.8 https://varunvemulapalli.com/blog/day-71-connecting-claude-to-your-tools-with-mcp/poster.jpgDay 71: Connecting Claude to your tools with MCP serversMCP servers give Claude a menu of tools for your systems, added with one command in Claude Code or as a connector in claude.ai.https://varunvemulapalli.com/blog/day-71-connecting-claude-to-your-tools-with-mcp/explainer.mp4103 https://varunvemulapalli.com/blog/day-72.html 2026-12-12 0.8 https://varunvemulapalli.com/blog/day-72-the-claude-agent-sdk-what-it-is/poster.jpgDay 72: The Claude Agent SDK: what it is and when to use itUse the API for single calls, Claude Code for hands-on work, and the Agent SDK when your own program needs an agent that reads, acts and loops without you.https://varunvemulapalli.com/blog/day-72-the-claude-agent-sdk-what-it-is/explainer.mp4105 https://varunvemulapalli.com/blog/day-73.html 2026-12-13 0.8 https://varunvemulapalli.com/blog/day-73-build-a-research-agent-with-the-claude/poster.jpgDay 73: Build a research agent with the Claude Agent SDKA research agent is the Agent SDK loop with search, read and write tools plus clear rules, and its brief is only as good as the citations you check.https://varunvemulapalli.com/blog/day-73-build-a-research-agent-with-the-claude/explainer.mp487 https://varunvemulapalli.com/blog/day-74.html 2026-12-14 0.8 https://varunvemulapalli.com/blog/day-74-subagents-hooks-and-permissions/poster.jpgDay 74: Subagents, hooks and permissionsSubagents split the work, hooks make steps automatic, and permission rules set hard limits that the model can't talk its way past.https://varunvemulapalli.com/blog/day-74-subagents-hooks-and-permissions/explainer.mp498 https://varunvemulapalli.com/blog/day-75.html 2026-12-15 0.8 https://varunvemulapalli.com/blog/day-75-hands-on-claude-code-builds-an-agent/poster.jpgDay 75: Hands-on: Claude Code builds an agent end to endDescribe the agent, review the plan, and let Claude Code build, test and run it, while you keep the approvals and the final decisions.https://varunvemulapalli.com/blog/day-75-hands-on-claude-code-builds-an-agent/explainer.mp494 https://varunvemulapalli.com/blog/day-76.html 2026-12-16 0.8 https://varunvemulapalli.com/blog/day-76-recap-of-days-55-75-comparing-the/poster.jpgDay 76: Recap of Days 55–75: comparing the coding agentsCopilot, Codex and Claude Code share the same core skills; pick by where your work happens and keep a human reviewing every change.https://varunvemulapalli.com/blog/day-76-recap-of-days-55-75-comparing-the/explainer.mp498 https://varunvemulapalli.com/blog/day-77.html 2026-12-17 0.8 https://varunvemulapalli.com/blog/day-77-what-copilot-studio-is-low-code-agents/poster.jpgDay 77: What Copilot Studio is: low-code agents for Microsoft 365Copilot Studio lets you assemble an agent from instructions, knowledge, tools, topics and triggers, and publish it where colleagues already work.https://varunvemulapalli.com/blog/day-77-what-copilot-studio-is-low-code-agents/explainer.mp4106 https://varunvemulapalli.com/blog/day-78.html 2026-12-18 0.8 https://varunvemulapalli.com/blog/day-78-your-first-agent-instructions-and-knowledge-sources/poster.jpgDay 78: Your first agent: instructions and knowledge sourcesClear instructions plus well-described knowledge turn a long manual into an agent that answers with citations.https://varunvemulapalli.com/blog/day-78-your-first-agent-instructions-and-knowledge-sources/explainer.mp498 https://varunvemulapalli.com/blog/day-79.html 2026-12-19 0.8 https://varunvemulapalli.com/blog/day-79-topics-triggers-and-conversation-design/poster.jpgDay 79: Topics, triggers and conversation designTopics give high-stakes conversations fixed, tested steps, while generative orchestration decides when to use them.https://varunvemulapalli.com/blog/day-79-topics-triggers-and-conversation-design/explainer.mp4101 https://varunvemulapalli.com/blog/day-80.html 2026-12-20 0.8 https://varunvemulapalli.com/blog/day-80-actions-connectors-power-automate-flows-and-apis/poster.jpgDay 80: Actions: connectors, Power Automate flows and APIsA tool, like an agent flow with clear inputs and outputs, turns your agent from an answerer into a doer.https://varunvemulapalli.com/blog/day-80-actions-connectors-power-automate-flows-and-apis/explainer.mp4108 https://varunvemulapalli.com/blog/day-81.html 2026-12-21 0.8 https://varunvemulapalli.com/blog/day-81-autonomous-agents-and-event-triggers/poster.jpgDay 81: Autonomous agents and event triggersEvent triggers let an agent start itself, so keep instructions precise, credentials in mind and a person on final decisions.https://varunvemulapalli.com/blog/day-81-autonomous-agents-and-event-triggers/explainer.mp4110 https://varunvemulapalli.com/blog/day-82.html 2026-12-22 0.8 https://varunvemulapalli.com/blog/day-82-publishing-to-teams-microsoft-365-copilot-and/poster.jpgDay 82: Publishing to Teams, Microsoft 365 Copilot and websitesPublish, pick channels where people already work, set authentication on purpose, and roll out from pilot to org with admin approval.https://varunvemulapalli.com/blog/day-82-publishing-to-teams-microsoft-365-copilot-and/explainer.mp4100 https://varunvemulapalli.com/blog/day-83.html 2026-12-23 0.8 https://varunvemulapalli.com/blog/day-83-security-governance-and-admin-controls/poster.jpgDay 83: Security, governance and admin controlsEnvironments, data policies, sign-in and audit logs let a company say yes to agent builders without losing control of its data.https://varunvemulapalli.com/blog/day-83-security-governance-and-admin-controls/explainer.mp4108 https://varunvemulapalli.com/blog/day-84.html 2026-12-24 0.8 https://varunvemulapalli.com/blog/day-84-hands-on-build-an-hr-policy-agent/poster.jpgDay 84: Hands-on: build an HR-policy agent in Copilot StudioA good policy agent answers from the documents, cites them, and hands personal cases to a human.https://varunvemulapalli.com/blog/day-84-hands-on-build-an-hr-policy-agent/explainer.mp495 https://varunvemulapalli.com/blog/day-85.html 2026-12-25 0.8 https://varunvemulapalli.com/blog/day-85-choosing-the-right-tool-claude-copilot-studio/poster.jpgDay 85: Choosing the right tool: Claude, Copilot Studio, Codex or GitHub CopilotPick the tool by who builds it, where users work, what it produces and what it must connect to, not by which demo looked best.https://varunvemulapalli.com/blog/day-85-choosing-the-right-tool-claude-copilot-studio/explainer.mp4102 https://varunvemulapalli.com/blog/day-86.html 2026-12-26 0.8 https://varunvemulapalli.com/blog/day-86-designing-your-agent-use-case-users-scope/poster.jpgDay 86: Designing your agent: use case, users, scope, success criteriaDesign an agent like a product: name the job, the users, the boundaries and the test for "done" before you write code.https://varunvemulapalli.com/blog/day-86-designing-your-agent-use-case-users-scope/explainer.mp4109 https://varunvemulapalli.com/blog/day-87.html 2026-12-27 0.8 https://varunvemulapalli.com/blog/day-87-writing-the-spec-and-system-prompt/poster.jpgDay 87: Writing the spec and system promptWrite the spec for humans first, then translate it into a system prompt with a role, clear rules, tags and an example.https://varunvemulapalli.com/blog/day-87-writing-the-spec-and-system-prompt/explainer.mp4103 https://varunvemulapalli.com/blog/day-88.html 2026-12-28 0.8 https://varunvemulapalli.com/blog/day-88-building-the-core-agent-loop/poster.jpgDay 88: Building the core agent loopThe agent loop is plain code: call the model, run the tool it asks for, send back the result, and stop when it's done or hits your limit.https://varunvemulapalli.com/blog/day-88-building-the-core-agent-loop/explainer.mp485 https://varunvemulapalli.com/blog/day-89.html 2026-12-29 0.8 https://varunvemulapalli.com/blog/day-89-adding-tools-and-actions/poster.jpgDay 89: Adding tools and actionsGive your agent reading tools freely, but put every action behind an approval gate your code enforces.https://varunvemulapalli.com/blog/day-89-adding-tools-and-actions/explainer.mp4106 https://varunvemulapalli.com/blog/day-90.html 2026-12-30 0.8 https://varunvemulapalli.com/blog/day-90-adding-knowledge-rag-and-knowledge-sources/poster.jpgDay 90: Adding knowledge (RAG and knowledge sources)Give your agent the team's glossary and owner directory, in the prompt while small, through retrieval when large, and keep both up to date.https://varunvemulapalli.com/blog/day-90-adding-knowledge-rag-and-knowledge-sources/explainer.mp488 https://varunvemulapalli.com/blog/day-91.html 2026-12-31 0.8 https://varunvemulapalli.com/blog/day-91-testing-and-evals-how-to-know-it/poster.jpgDay 91: Testing and evals: how to know it worksAn eval is a fixed exam of inputs and golden answers that turns "it seems to work" into a score you rerun after every change.https://varunvemulapalli.com/blog/day-91-testing-and-evals-how-to-know-it/explainer.mp4103 https://varunvemulapalli.com/blog/day-92.html 2027-01-01 0.8 https://varunvemulapalli.com/blog/day-92-cost-latency-and-monitoring/poster.jpgDay 92: Cost, latency and monitoringLog every run to know cost, seconds and errors per run; resent input tokens are usually the biggest lever.https://varunvemulapalli.com/blog/day-92-cost-latency-and-monitoring/explainer.mp4105 https://varunvemulapalli.com/blog/day-93.html 2027-01-02 0.8 https://varunvemulapalli.com/blog/day-93-security-and-responsible-ai-checklist/poster.jpgDay 93: Security and responsible-AI checklistTreat every transcript as untrusted data, give tools the least power they need, mask PII, and keep a human approval before anything is created or sent.https://varunvemulapalli.com/blog/day-93-security-and-responsible-ai-checklist/explainer.mp4108 https://varunvemulapalli.com/blog/day-94.html 2027-01-03 0.8 https://varunvemulapalli.com/blog/day-94-deploying-and-sharing-your-agent/poster.jpgDay 94: Deploying and sharing your agentShare your agent one rung at a time, from your laptop to a teammate to a small private web app, and hand the organization-wide version to IT.https://varunvemulapalli.com/blog/day-94-deploying-and-sharing-your-agent/explainer.mp4100 https://varunvemulapalli.com/blog/day-95.html 2027-01-04 0.8 https://varunvemulapalli.com/blog/day-95-collecting-feedback-and-iterating/poster.jpgDay 95: Collecting feedback and iteratingLog every approval, edit and thumbs-down, fix the biggest bucket one change at a time, and turn each failure into a new eval case.https://varunvemulapalli.com/blog/day-95-collecting-feedback-and-iterating/explainer.mp488 https://varunvemulapalli.com/blog/day-96.html 2027-01-05 0.8 https://varunvemulapalli.com/blog/day-96-showcase-it-readme-demo-video-and-github/poster.jpgDay 96: Showcase it: README, demo video and GitHub portfolioA one-line README, a 90-second demo and a pinned repo turn your agent into proof anyone can check in 2 minutes.https://varunvemulapalli.com/blog/day-96-showcase-it-readme-demo-video-and-github/explainer.mp490 https://varunvemulapalli.com/blog/day-97.html 2027-01-06 0.8 https://varunvemulapalli.com/blog/day-97-agents-at-work-real-use-cases-in/poster.jpgDay 97: Agents at work: real use cases in banking, insurance and healthcareAgents at work do the legwork around a decision (gather, check, draft, log) while a person keeps the decision.https://varunvemulapalli.com/blog/day-97-agents-at-work-real-use-cases-in/explainer.mp4114 https://varunvemulapalli.com/blog/day-98.html 2027-01-07 0.8 https://varunvemulapalli.com/blog/day-98-responsible-ai-bias-privacy-and-regulation/poster.jpgDay 98: Responsible AI: bias, privacy and regulationTest outcomes by group, send only the data you need, and know which rules apply before you launch.https://varunvemulapalli.com/blog/day-98-responsible-ai-bias-privacy-and-regulation/explainer.mp4104 https://varunvemulapalli.com/blog/day-99.html 2027-01-08 0.8 https://varunvemulapalli.com/blog/day-99-your-roadmap-after-100-days/poster.jpgDay 99: Your roadmap after 100 daysPick one real problem and give it 90 days: use it safely, build it, then ship it and show it.https://varunvemulapalli.com/blog/day-99-your-roadmap-after-100-days/explainer.mp492 https://varunvemulapalli.com/blog/day-100.html 2027-01-09 0.8 https://varunvemulapalli.com/blog/day-100-reflection-100-days-later-and-what-s/poster.jpgDay 100: Reflection: 100 days later, and what's nextYou started with "what is AI?" and finished able to design, build, test and ship an agent responsibly.https://varunvemulapalli.com/blog/day-100-reflection-100-days-later-and-what-s/explainer.mp494