Notifications
Clear all
Topic starter
19/08/2026 3:50 pm
TL;DR: Agentic coding can multiply engineering output when teams shift from typing to orchestration, according to Sawmills, but the same workflow also exposes a hard limit: agents are fast, context-hungry, and confidently wrong without test-backed verification. The governance lesson is that delegation scales only when boundaries, validation, and human review stay explicit.
NHIMG editorial — based on content published by Sawmills: How Agentic Engineering Unlocked 10x More Execution News
Questions worth separating out
Q: How should teams govern AI-generated code when they cannot review every change?
A: Teams should shift from source-only assurance to runtime assurance.
Q: Why do agentic coding workflows need stronger verification than normal developer tooling?
A: Because the agent can complete a task exactly as described and still produce incorrect or unsafe output if the instruction was incomplete.
Q: What do security teams get wrong about AI agents in CI/CD pipelines?
A: Teams often assume an agent is just another automation step, when in practice it can interpret untrusted text and take actions with real permissions.
Practitioner guidance
- Define execution boundaries for coding agents Limit which repositories, commands, and environments an agent may touch.
- Make tests the merge gate for agent output Require automated tests and linting to pass before any agent-generated pull request can be merged.
- Break work into small, auditable tasks Use narrow prompts, single-purpose diffs, and staged review points so each step can be checked independently.
What's in the full article
Sawmills' full article covers the operational detail this post intentionally leaves for the source:
- The exact orchestration workflow used to route planning, execution, and review across multiple model types
- The day-by-day account of how the 28 PR afternoon worked across 13 services and what broke during early experimentation
- The specific division between fast and reasoning models for simple versus complex changes
- The practical examples of test-first task design, decomposition, and when the CTO chose not to delegate
👉 Read Sawmills' analysis of agentic engineering and AI-assisted pull requests →
Agentic coding and AI-assisted PRs: where is the governance gap?
Explore further
19/08/2026 4:26 pm
Agentic engineering creates a new governance boundary between assistance and delegated execution. Once a system can run shells, change files, and open PRs, it is no longer just a productivity aid. The control question becomes who authorised the action, under what constraints, and with what evidence of correctness. That is a human identity and NHI governance issue at the same time, because the agent behaves like a non-human actor inside a privileged delivery workflow.
A question worth separating out:
Q: When should organisations keep coding tasks human instead of delegating them to agents?
A: Keep tasks human when failure is expensive and verification is hard, especially for security architecture, incident response, or novel changes that affect multiple systems. Delegation works best for bounded, testable work where the output can be checked automatically and the blast radius is limited.
👉 Read our full editorial: Agentic coding boosts output, but verification still sets the limit
