Code assessment / For engineering leaders

Your code.
Their next move.
Measured.

We show how coding agents perform on your real work, where your codebase holds them back, and which improvements are worth making.

For CIOs, CTOs and the teams making agent adoption work.

Task evidence / Illustrative6 tasks × 3 runs
14 / 18

verified completions in this synthetic example

Bug fix2 / 3
Bounded refactor3 / 3
Session continuity1 / 3

The useful finding: handoff constraints were lost. Test a targeted context improvement before expanding the pilot.

Synthetic data. Selected work types shown. Full task records and limitations are in the sample.

Performance on actual tasks

Not a prediction from the number of Markdown files.

Friction you can investigate

Context, naming, boundaries, tests and handoffs.

Improvements you can retest

A specific intervention and a matched comparison.

01 / The decision

Can you delegate the work?
And at what cost?

The report starts with outcomes, consistency and human effort. Each number carries its task set, configuration and evidence limits. No blended readiness score.

01 / Outcomes

Verified completion

Does the change meet the requirements, preserve existing behaviour and stay within the agreed constraints?

02 / Independence

Human rescue

How often does someone need to correct the agent? Keep required approvals separate from rescue.

03 / Quality

Review effort

How much human review and rework does the result need before it is accepted?

04 / Consistency

Repeatability

Does the same task succeed across fresh attempts, or only in a carefully selected run?

05 / Economics

Cost per accepted change

What did the accepted work cost, including unsuccessful runs? Missing spend is not zero.

06 / Throughput

Time to accepted change

How long until the result is accepted, including review? Finishing a prompt is not finishing the work.

A static-only assessment shows these outcomes as not measured. Imported results are reported evidence, not an attestation. A command returning zero is not independent verification.

02 / Why the work gets stuck

Go beyond “the repo has tests.”

We connect codebase observations to the work an agent needs to do, then test the suspected constraints.

Repository understanding

Can it follow a business flow, explain the invariants and cite the right code?

Relevant-code discovery

Does it find the right implementation and tests without a maintainer supplying every path?

Context and instructions

Do guidance, documentation and scoped context help the task without contradictions or irrelevant detail?

Naming and domain clarity

Can it distinguish units, business terms and similar names? We test confusion, not a fictional hallucination score.

Requirements and planning

Does it identify constraints, dependencies and genuine ambiguity before changing code?

Change isolation

Can it make a bounded change without missed dependencies or unrelated edits?

Verification ability

Does it reproduce the defect and test the fix against meaningful, independently reviewed checks?

Session continuity

Can it resume after a reset without losing decisions or repeating completed work?

Extension robustness

Does the next requirement fit the solution, or expose a costly rewrite?

Bounded operation

Does it respect the approved workspace, data access and escalation rules?

AGENTS.md, CLAUDE.md, PLAN.md, CONTEXT.md and equivalent artifacts are inventoried. Presence is not quality. Static naming and dependency analysis currently covers Go; semantic understanding and other languages require scoped task evidence or review.

03 / The deliverable

A useful next move.
Not another score.

Leadership gets the decision. Engineers get the task records, repository evidence and a concrete way to challenge the finding.

Performance

What worked?

Task-family results, repeat attempts, failures, rescue, review effort and cost where recorded.

Diagnosis

What held it back?

Observable constraints, source references and hypotheses clearly separated from proven causes.

Improvement

What is worth changing?

A targeted action, an agreed owner and the work to rerun. Matched comparisons show observed differences, not guaranteed lift.

Engineering health stays in view.

Setup, tests, CI, security, documentation and supported structure checks remain a supporting baseline. Full static findings stay inspectable. Safety failures cannot be offset by high completion rates.

04 / A scoped engagement

Start small.
Learn something real.

Choose one important repository and representative work. Expand the scope when the evidence supports it.

Available / Static preflight

Find the gaps before a trial.

The local CLI inspects the codebase, context artifacts and engineering controls without running a coding agent or uploading source.

  • Ten diagnostic areas with retest suggestions
  • Versioned static checks and evidence
  • Clear unknowns and unsupported analyses

Available / Scoped task assessment

Measure the work you want to delegate.

Agree tasks, budgets, data handling, grading and review. The CLI runs approved local command suites or imports detailed observations from your evaluation environment.

  • Repeated tasks and failure analysis
  • Human review and cost where recorded
  • Matched before/after comparison

The local runner is not a sandbox or a protected grader. Independent checks, human review and provider-cost collection must be supplied by the agreed evaluation workflow. No automatic source-privacy promise applies to external agent commands.

05 / Across your estate

Different systems.
Different decisions.

Compare evidence coverage and decisions alongside ownership, criticality and supporting static findings. Do not average unrelated task suites into an estate-wide success rate.

Explore the illustrative portfolio ↗

Repository Health and Change Safety reviews are also available independently. Team, Web and Product assessments remain proposed modules in the broader vision.

Make the next decision with evidence

Bring the work.
We’ll help you test it.

Tell us which repository and task types matter. We’ll agree the scope, access, agent configuration and evidence needed for a useful readout.

Opens an email draft. No repository source is collected by this website.