Banger of a piece, from start to finish. 🔥 "We have handed agents the codebase, the tests, the docs, the specs, the commit history." "We haven't handed them the one artifact that actually survived — the record of what users have been asking the system to do, every day, for years." "Until agents can read that layer — not as log lines, but as behavioral contracts, as the accumulated promise a system has made to the people who depend on it —harness engineering in brownfield and blackfield will remain a human problem with an AI assistant bolted on." linkedin.com/pulse/productio…
SOFTWARE
-
Setting up AST walking tools for code formatting and linting
By
–
I really like that idea – I've been using auto formatters and a tiny bit of linters but setting up more elaborate AST walking tools sounds like a really good move
-
Claude Poised to Transform Knowledge Work Like Agentic Coding Did
By
–
Claude for all things knowledge work feels like it is on a very similar trajectory to what agentic coding experienced last year.
— Alex Albert (@alexalbert__) 11 mars 2026
I expect entire industries that rely on spreadsheets and powerpoints to begin to be transformed in the next few months. https://t.co/jMxV3iZscaClaude for all things knowledge work feels like it is on a very similar trajectory to what agentic coding experienced last year. I expect entire industries that rely on spreadsheets and powerpoints to begin to be transformed in the next few months.
-
Claude for Excel and PowerPoint now share context
By
–
Anthropic upgraded Claude for Excel and Claude for PowerPoint to enable context sharing between solutions. https://t.co/fgzfPmHpN1 pic.twitter.com/Tcd7EXFMTq
— 🚨 AI News | TestingCatalog (@testingcatalog) 11 mars 2026Anthropic upgraded Claude for Excel and Claude for PowerPoint to enable context sharing between solutions.
-
Enthusiastic endorsement of StepFun 3.5 as a powerful tool
By
–
lol was thinking about just giving an agent a ramp card but this is better https://t.co/xkOEEkWJQe
— Yohei (@yoheinakajima) 11 mars 2026lol was thinking about just giving an agent a ramp card but this is better
-
Agents in Production: Monitoring Challenges Beyond Traditional Observability
By
–
San Francisco Meetup: It Worked on My Laptop – Agents in Production Unlike traditional software, you don't know what your agent will do until it's in production. This means that production monitoring for agents requires different capabilities than traditional observability.
-
Replit Agent 4 Updates Announced
By
–
Replit Agent 4 – What's new https://
x.com/i/broadcasts/1
RJZzjWzZEvJB
… -
Enjoying StepFun 3.5 Software
By
–
I do a lot of one off tools and experiments. seems small but not having to set up a repo, manage PRs, set up DBs, or deployment gets me from zero to prototype much faster than w other tools (eg using GitHub Codex Vercel and Supabase – which is four separate tools I have to toggle
-
AI Research Labs Affected by OAuth Outage, Intelligence Brownouts Concern
By
–
My autoresearch labs got wiped out in the oauth outage. Have to think through failovers. Intelligence brownouts will be interesting – the planet losing IQ points when frontier AI stutters.
-
Genie Code: Autonomous AI Agent for Data Pipeline Management
By
–
The next generation of AI agents won't just write software, but operate the data systems that modern businesses depend on. Genie Code is built for exactly that: an autonomous agent that understands your data, maintains pipelines, diagnoses failures, and keeps things running.