proomt

Search

Search posts, papers, and topics

All posts

TemporalPaul Oh7 min readintermediate

Using coding agents on a migration: Three practices that mattered

Summary

Coding agents proved most effective for cleaning up temporary code and legacy configurations during a migration, rather than for initial code construction. This effectiveness stemmed from three specific practices: documenting cleanup needs upfront, co-locating rules with code and their enforcement, and actively managing instruction staleness.

  • Document cleanup instructions for temporary code at creation time, using distinct markers for agents to find later.
  • Co-locate durable rules with the code they govern, explicitly naming the regression tests or mechanisms that enforce them.
  • Treat agent instructions as living artifacts that can go stale; integrate their maintenance into documentation processes.
  • Coding agents are particularly effective for exhaustive, tedious cleanup tasks that engineers often defer indefinitely.

Engineers using or considering coding agents, or those managing technical debt, should care as these practices improve agent utility and reduce long-term code cruft.

7/10

Related reading

  1. Brownfield Agentic Engineering

    Addy Osmani outlines a pragmatic framework for safely introducing AI‑driven agents into legacy (brownfield) codebases. He proposes zoning code by risk, documenting non‑code knowledge, preserving research in durable memos, building a reusable “harness” of tools and rules, and starting with zero‑risk, characterization‑test‑driven work.

    Addy Osmaniaddyosmani.com13 min
  2. Towards Self-Driving Codebases

    The post argues that AI agents could eventually handle low‑level engineering tasks—bug fixing, debugging, UI consistency, growth experiments—if the dev toolchain is made “agent‑legible”. It outlines missing primitives (global memory, code‑base rot prevention, better dev environments) and proposes a bootstrapping process to measure and improve a repo’s “agent readiness”. The piece is largely specu…

    Hacker News front pagedetail.dev9 minHN12099
  3. CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

    CodeMidas builds RL environments directly from open‑source code: agents explore a repo, infer a spec, generate tests from the original implementation, and filter tasks via execution checks. The pipeline yields 5,545 high‑quality coding tasks across 23 languages and 15 domains. Training the MiMo‑V2.5 agent with GRPO on this dataset improves benchmark scores by 8‑18% (e.g., DeepSWE +11.7%, ProgramB…

    Hugging Face Daily Papersarxiv.org1 minpaper
  4. Agentic Skill Decay

    Addy Osmani warns that AI agents can short‑circuit the hands‑on practice (“reps”) that builds deep expertise and judgment. He recommends deliberately inserting hypothesis‑forming, “why” questioning, diff inspection, failure prediction, and occasional manual coding into the workflow, especially for junior engineers. A 2026 Anthropic study showed junior developers using AI scored 17 % lower on a fo…

    Addy Osmaniaddyosmani.com16 min
  5. Agentic DevOps World 2026: Key Takeaways

    Enterprise AI code generation is outpacing governance: 92% of leaders feel confident but 81% see more production issues; post‑generation stages (review, testing, deployment) are now the bottleneck. Successful adoption requires up‑skilling, end‑to‑end metrics, and tooling (e.g., CloudBees DevOps Agent Kit, PR‑auto‑approval agents).

    Codeshipcloudbees.com8 min