Guides

Coding tasks & verification

Run coding agents with company + repo context, then independently verify before treating work as delivered.

Last updated 2026-07-27

Coding tasks are how HiveBase supervises coding agents against business intent and repository context, not just a green CI check. Agents propose; verification judges whether the work is actually delivered. Product surface: /tasks/code.

Overview: Tasks. Connected agents: Agents. Repos: GitHub.

Producer ≠ verifier

The agent that produces a change is not the final judge of “done.” HiveBase separates execution from verification so “completed” stays a claim until evidence supports a verification verdict.

  1. 01

    Intent + context

    Brain + repo + brief

  2. 02

    Agent proposes

    Diff / PR

  3. 03

    Verification

    Independent scorecard

  4. 04

    Verdict

    Verified or held

  5. 05

    You / merge policy

    Still gated

Producer ≠ verifier — “completed” stays a claim until evidence supports a verdict.

What coding tasks use for context

SourceRole
Company BrainWhy this work exists — customers, decisions, constraints
Connected reposWhat the code actually is
Task briefAcceptance criteria and scope
Agent hostCursor, Claude Code, Codex, OpenCode (etc.) as runners

Verification in plain language

Typical verdict shapes (labels may vary in product UI):

VerdictMeaning
VerifiedChecks / evidence support the reviewed head
ReviewedDiff and risks examined; strong executed proof may still be missing
UnverifiedEvidence too thin — gaps named, not over-claimed
StaleNewer pushes invalidated the prior head; re-verify

Completed is a claim. Delivered is a verdict.

Trust defaults

  • Merge, force-push, and destructive git operations are not silent.
  • GitHub writeback follows fail-closed certification — see GitHub.
  • Every consequential apply path can leave an action receipt.