<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Kiran Chanda</title><description>A calm, editorial home for everything Kiran Chanda writes, shares, and teaches — articles, notes, and videos on AI agents, APIs, search, and engineering leadership.</description><link>https://deepwissen.com/</link><language>en-us</language><item><title>Article: Your Coding Agent Is Making Architectural Decisions Without Telling You</title><link>https://deepwissen.com/articles/your-coding-agent-is-making-architectural-decisions/</link><guid isPermaLink="true">https://deepwissen.com/articles/your-coding-agent-is-making-architectural-decisions/</guid><description>It knows fifty design patterns — that&apos;s the problem. The most dangerous case isn&apos;t when it picks a bad pattern; it&apos;s when it picks a reasonable one, commits it as if you&apos;d decided, and never mentions a choice was made.</description><pubDate>Fri, 14 Aug 2026 00:00:00 GMT</pubDate><category>AI Agents</category><category>Architecture</category><category>Technology Leadership</category></item><item><title>Video: The 5 Ways AI Agents Call Your APIs (Course Intro)</title><link>https://deepwissen.com/videos/the-5-ways-ai-agents-call-your-apis-course-intro/</link><guid isPermaLink="true">https://deepwissen.com/videos/the-5-ways-ai-agents-call-your-apis-course-intro/</guid><description>An introduction to the five patterns for connecting AI agents to your existing APIs.</description><pubDate>Thu, 13 Aug 2026 00:00:00 GMT</pubDate><category>AI Agents</category><category>API Architecture</category></item><item><title>Video: How APIs Actually Work — Foundations for AI Agents</title><link>https://deepwissen.com/videos/how-apis-actually-work/</link><guid isPermaLink="true">https://deepwissen.com/videos/how-apis-actually-work/</guid><description>The API foundations you need before letting an AI agent call your services.</description><pubDate>Tue, 11 Aug 2026 00:00:00 GMT</pubDate><category>API Architecture</category><category>AI Agents</category></item><item><title>Video: The Tool-Layer Decision: 5 Ways AI Calls Your APIs</title><link>https://deepwissen.com/videos/the-tool-layer-decision/</link><guid isPermaLink="true">https://deepwissen.com/videos/the-tool-layer-decision/</guid><description>Choosing the right tool layer — the five ways an AI agent can call your APIs, and when to use each.</description><pubDate>Sun, 09 Aug 2026 00:00:00 GMT</pubDate><category>AI Agents</category><category>API Architecture</category></item><item><title>Video: CodeAgent interviewing AI Preflight</title><link>https://deepwissen.com/videos/codeagent-interviewing-ai-preflight/</link><guid isPermaLink="true">https://deepwissen.com/videos/codeagent-interviewing-ai-preflight/</guid><description>A CodeAgent walkthrough — interviewing an AI before it runs (preflight).</description><pubDate>Fri, 07 Aug 2026 00:00:00 GMT</pubDate><category>AI Agents</category></item><item><title>Article: The Real Reason Your AI Coding Assistant Keeps Getting It Wrong</title><link>https://deepwissen.com/articles/the-real-reason-your-ai-coding-assistant-keeps-getting-it-wrong/</link><guid isPermaLink="true">https://deepwissen.com/articles/the-real-reason-your-ai-coding-assistant-keeps-getting-it-wrong/</guid><description>It&apos;s not the model — it&apos;s what you&apos;re feeding it. Why the context pipeline, not the LLM, is where the real performance and cost gap lives.</description><pubDate>Wed, 01 Apr 2026 00:00:00 GMT</pubDate><category>AI Agents</category><category>Product Engineering</category></item><item><title>Article: What 1-Minute Videos Got Wrong About Claude&apos;s C Compiler</title><link>https://deepwissen.com/articles/what-1-minute-videos-got-wrong-about-claudes-c-compiler/</link><guid isPermaLink="true">https://deepwissen.com/articles/what-1-minute-videos-got-wrong-about-claudes-c-compiler/</guid><description>A viral clip claimed AI autonomously built a C compiler and replaced developers. Reading the actual engineering post tells a calmer, more interesting story.</description><pubDate>Fri, 13 Feb 2026 00:00:00 GMT</pubDate><category>AI Agents</category><category>Technology Leadership</category></item><item><title>Article: One Year Working With AI Agents — What Actually Changed</title><link>https://deepwissen.com/articles/one-year-working-with-ai-agents/</link><guid isPermaLink="true">https://deepwissen.com/articles/one-year-working-with-ai-agents/</guid><description>I thought AI would help me write code faster. What actually changed was everything else about the job.</description><pubDate>Thu, 05 Feb 2026 00:00:00 GMT</pubDate><category>AI Agents</category><category>Technology Leadership</category></item><item><title>Article: Machine-Readable Isn&apos;t Machine Understanding — And That Used to Be Fine</title><link>https://deepwissen.com/articles/machine-readable-isnt-machine-understanding/</link><guid isPermaLink="true">https://deepwissen.com/articles/machine-readable-isnt-machine-understanding/</guid><description>Why the Semantic Web was 25 years early, and why AI agents just made explicit meaning unavoidable.</description><pubDate>Fri, 19 Dec 2025 00:00:00 GMT</pubDate><category>AI Agents</category><category>API Architecture</category><category>MCP</category></item><item><title>Article: AI Never Disagrees — And That&apos;s the Problem</title><link>https://deepwissen.com/articles/ai-never-disagrees/</link><guid isPermaLink="true">https://deepwissen.com/articles/ai-never-disagrees/</guid><description>AI mirrors your enthusiasm instead of challenging you. Why that&apos;s dangerous, and how to deliberately engineer disagreement into your process.</description><pubDate>Mon, 03 Nov 2025 00:00:00 GMT</pubDate><category>AI Agents</category><category>Technology Leadership</category></item><item><title>Article: Are We Cultivating Innovation — or Technical Debt?</title><link>https://deepwissen.com/articles/are-we-cultivating-innovation-or-technical-debt/</link><guid isPermaLink="true">https://deepwissen.com/articles/are-we-cultivating-innovation-or-technical-debt/</guid><description>AI lets everyone &apos;grow&apos; software fast. But without understanding the soil — architecture, security, maintainability — we may just be accumulating debt faster.</description><pubDate>Tue, 07 Oct 2025 00:00:00 GMT</pubDate><category>AI Agents</category><category>Product Engineering</category><category>Architecture</category></item><item><title>Article: AI Makes Code Work. Engineers Make It Right.</title><link>https://deepwissen.com/articles/ai-makes-code-work-engineers-make-it-right/</link><guid isPermaLink="true">https://deepwissen.com/articles/ai-makes-code-work-engineers-make-it-right/</guid><description>Part 1: Agile user stories work because humans fill the gaps with context. Hand those same lightweight stories to an AI and the gaps become dangerous.</description><pubDate>Sat, 13 Sep 2025 00:00:00 GMT</pubDate><category>AI Agents</category><category>Product Engineering</category></item><item><title>Article: Stop Rebuilding for AI Integrations: Use Your Existing REST APIs with MCP</title><link>https://deepwissen.com/articles/mcp-rest-pattern/</link><guid isPermaLink="true">https://deepwissen.com/articles/mcp-rest-pattern/</guid><description>The MCP → REST pattern: one protocol-adapter service makes your existing REST microservices AI-accessible — no rebuilding required.</description><pubDate>Sun, 20 Jul 2025 00:00:00 GMT</pubDate><category>MCP</category><category>API Architecture</category><category>AI Agents</category></item><item><title>Article: How GitHub Copilot Agent Mode Appears to Work: A Reverse-Engineering Deep Dive</title><link>https://deepwissen.com/articles/how-github-copilot-agent-mode-appears-to-work/</link><guid isPermaLink="true">https://deepwissen.com/articles/how-github-copilot-agent-mode-appears-to-work/</guid><description>After reverse-engineering the GitHub Copilot extension, here&apos;s how Agent Mode appears to index your codebase, search it, and act with 16+ specialized tools.</description><pubDate>Fri, 06 Jun 2025 00:00:00 GMT</pubDate><category>AI Agents</category><category>Architecture</category></item><item><title>Article: AI Security Vulnerabilities: Understanding Jailbreaking Attack Vectors</title><link>https://deepwissen.com/articles/ai-jailbreaking-attack-vectors/</link><guid isPermaLink="true">https://deepwissen.com/articles/ai-jailbreaking-attack-vectors/</guid><description>How &apos;jailbreaking&apos; tricks AI systems into ignoring their safety rules — including the &apos;Affirmation Jailbreak&apos; — and how providers and teams defend against it.</description><pubDate>Tue, 13 May 2025 00:00:00 GMT</pubDate><category>Security</category><category>AI Agents</category></item><item><title>Article: Reinforcement Learning: How AI Learns Through Trial &amp; Error</title><link>https://deepwissen.com/articles/reinforcement-learning-trial-and-error/</link><guid isPermaLink="true">https://deepwissen.com/articles/reinforcement-learning-trial-and-error/</guid><description>Markov Decision Processes and the Bellman equation, explained with a robot vacuum and a treasure-hunt grid — the secret sauce behind how AI learns to make smart decisions.</description><pubDate>Thu, 01 May 2025 00:00:00 GMT</pubDate><category>AI Agents</category></item><item><title>Article: GitHub Copilot Agent Mode: Productivity at the Expense of Security?</title><link>https://deepwissen.com/articles/copilot-agent-mode-productivity-vs-security/</link><guid isPermaLink="true">https://deepwissen.com/articles/copilot-agent-mode-productivity-vs-security/</guid><description>Agent Mode runs with your full privileges and no built-in guardrails — and the &apos;Rules File Backdoor&apos; attack shows how hidden instructions can turn it against you.</description><pubDate>Sat, 26 Apr 2025 00:00:00 GMT</pubDate><category>Security</category><category>AI Agents</category></item><item><title>Article: GitHub Copilot: A Developer&apos;s Powerful Ally — With the Right Guidance</title><link>https://deepwissen.com/articles/github-copilot-a-developers-powerful-ally/</link><guid isPermaLink="true">https://deepwissen.com/articles/github-copilot-a-developers-powerful-ally/</guid><description>Copilot is a productivity multiplier, but only when you lead and it follows. Practical prompting, review, clean-code, and team practices for getting real value.</description><pubDate>Sat, 12 Apr 2025 00:00:00 GMT</pubDate><category>AI Agents</category><category>Product Engineering</category></item><item><title>Article: Finding Balance in the AI Age: Lessons from &apos;The Wild Robot&apos;</title><link>https://deepwissen.com/articles/finding-balance-lessons-from-the-wild-robot/</link><guid isPermaLink="true">https://deepwissen.com/articles/finding-balance-lessons-from-the-wild-robot/</guid><description>A robot teaching a gosling to survive by checking off tasks is a surprisingly good metaphor for how junior developers are learning to code with AI.</description><pubDate>Tue, 01 Apr 2025 00:00:00 GMT</pubDate><category>AI Agents</category><category>Technology Leadership</category></item><item><title>Article: Exploring DeepSeek R1 Distilled Models on Raspberry Pi 5</title><link>https://deepwissen.com/articles/deepseek-r1-on-raspberry-pi-5/</link><guid isPermaLink="true">https://deepwissen.com/articles/deepseek-r1-on-raspberry-pi-5/</guid><description>Running DeepSeek R1&apos;s distilled reasoning models locally on a Raspberry Pi 5 — what worked, what didn&apos;t, and why local AI is worth the experiment.</description><pubDate>Wed, 05 Feb 2025 00:00:00 GMT</pubDate><category>AI Agents</category><category>Product Engineering</category></item></channel></rss>