Another batch of articles today that impacted my thinking. Thanks to today’s reading list, I installed the MCP server for our Google Developer Knowledge API, realized I was thinking about MCP wrong, and felt grateful for the job changes I didn’t make.

[blog] Introducing the Developer Knowledge API and MCP Server (https://developers.googleblog.com/introducing-the-developer-knowledge-api-and-mcp-server/). This is the best thing we’ll deliver this week. Developers (and AI tools) can now access a single source of truth for information about Google products.

[article] Three ways AI will change engineering practices (https://www.infoworld.com/article/4123664/three-ways-ai-will-change-engineering-practices.html). Don’t disagree with this. Have you planned for each?

[article] To Drive AI Adoption, Build Your Team’s Product Management Skills (https://hbr.org/2026/02/to-drive-ai-adoption-build-your-teams-product-management-skills). It’s likely confirmation bias, but I’m noticing a LOT of conversation about the value of a product management discipline when embracing AI.

[blog] Context Management and MCP (https://cra.mr/context-management-and-mcp). Wow, my favorite post of the day. It definitely made me rethink some things token consumption and Skills.

[blog] Forget technical debt (https://www.ufried.com/blog/forget_technical_debt/). The point here is that focusing purely on technical debt isn’t sufficient to fixing the problems in the system.

[article] What Happens When Technical Debt Vanishes? (https://ieeexplore.ieee.org/document/11316905) More thought experiments about technical debt! This was a compelling read.

[article] IT leaders grapple with AI agent sprawl (https://www.ciodive.com/news/it-leaders-grapple-ai-agent-sprawl-integration/811411/). New source of debt, incoming! Companies need to get a handle on their agents, data, and integrations.

[blog] Easy FunctionGemma finetuning with Tunix on Google TPUs (https://developers.googleblog.com/easy-functiongemma-finetuning-with-tunix-on-google-tpus/). I learned like four things from this post, and I’m tempted to actually run this example scenario myself!

[article] Anthropic releases Opus 4.6 with new ‘agent teams’ (https://techcrunch.com/2026/02/05/anthropic-releases-opus-4-6-with-new-agent-teams/). Is it model update season already? We’ve already made this one available on Vertex AI (https://cloud.google.com/blog/products/ai-machine-learning/expanding-vertex-ai-with-claude-opus-4-6/). OpenAI gave Anthropic about ten minutes in the spotlight (https://techcrunch.com/2026/02/05/openai-launches-new-agentic-coding-model-only-minutes-after-anthropic-drops-its-own/).

[article] 4 self-contained databases for your apps (https://www.infoworld.com/article/4125081/4-self-contained-databases-for-your-apps.html). Which databases offer you a no-install binary that’s portable? I’m not sure I thought of this whole set.

[blog] Antigravity the Ralph Wiggum style (https://medium.com/google-cloud/antigravity-the-ralph-wiggum-style-ee6784a78237). Turn your agent-building tool loose and let it relentless tackle a problem until it reaches the goal? It’s not for every case, but seeing this approach may spark ideas.

[article] Kilo CLI 1.0 brings open source vibe coding to your terminal with support for 500+ models (https://venturebeat.com/orchestration/kilo-cli-1-0-brings-open-source-vibe-coding-to-your-terminal-with-support). Interesting. These types of tools are getting so powerful.

[blog] I left FAANG for a startup and regretted it (https://lawrenceztang.substack.com/p/i-left-faang-for-a-startup-and-regretted). We only seem to hear stories of raging successes after leaving a BIG TECH job. It’s useful to see a different perspective.

Want to get this update sent to you every day? Subscribe to my RSS feed (https://seroter.com/feed/) or subscribe via email below:

					Subscribe (https://seroter.com/?post_type=post&p=28408)