Muthukrishnan Bommiah · muthub.org
AI has made writing code cheap. Verification, trusted context and human judgment are now the scarce resources, and teams that redesign their lifecycle around them will pull away from teams that only add assistants.
AI-native SDLC6 min readThe knowledge an agent needs is scattered across code, tickets, chat, wikis, incident tools and people's heads. Each fragment is accurate and useless alone. Fragmentation, more than model quality, is what makes enterprise agents brittle.
Context engineering6 min readHanding an AI agent a production codebase without a harness is like putting a teenager in a sports car with no dual brakes. Deterministic guardrails and sensors, owned as a platform, are what make agents safe to scale.
Governed AI6 min readAI now writes code faster than any review board can read it, while architecture still moves at meeting speed. Governance has to become something that executes in the pipeline and in the agent's context.
Governed AI6 min readPlatform-embedded, sandboxed and evolutionary coding agents each earn trust in a different way. Then the editor became a fleet manager. Choose and govern agents by how their work will be verified.
AI-native SDLC6 min readData platforms built for people asking questions will strain when the main consumer is software taking actions. Five principles for designing data platforms where agents are first-class users, and why an open lakehouse helps.
Data & AI platforms6 min readPython is unrivaled for research and prototyping. Production enterprise AI is mostly integration, security and scale, and with JVM agent frameworks now arriving, the runtime that owns the transaction is often the right home for the agent.
Data & AI platforms5 min readAgents act on their own, at machine speed, across many systems. Static credentials and perimeter thinking don't hold up. Attested identity, explicit delegation and policy enforced outside the model do.
Governed AI5 min readEditors now run local, background and cloud agents side by side. The leadership job shifts from writing code to designing the system that writes it.
Note1 min readHigh-level SDKs break under real tool use. Caching, reinforcement, failure isolation and shared state decide whether an agent is reliable.
Note1 min readThe lakehouse unified analytics and AI. Bringing operational Postgres into it points toward one governed source of truth for agents.
Note1 min readAd-hoc prompting yields code that looks right but misses intent. Making the spec the gated source of truth is how AI-assisted delivery becomes repeatable.
Note1 min readAn agent that runs the tests, reads the failure and fixes its own work is the line between autonomy and a one-shot tool.
Note1 min readAn experimental agent built pipelines, changed schemas, reverted its own mistakes and generated quality checks from plain language. Self-correction was the part that mattered.
Note1 min readDirect remote MCP access through the Messages API removed a client layer and moved agent integration from clever hacks toward engineering.
Note1 min readMCP connects agents to tools; Agent2Agent connects agents to each other. Together they turn single agents into systems, and raise the governance stakes.
Note1 min read