cd /news/developer-tools/testing-agent-experience-in-agent-na… · home topics developer-tools article
[ARTICLE · art-114386] src=github.com ↗ pub= topic=developer-tools verified=true sentiment=· neutral

Testing Agent Experience in Agent-Native Dev Tools

Shen Li released DevTool AX Kit, a local-first toolkit for testing agent-native developer tools, which captures agent runs, verifies outcomes with independent checks, and safely replays external effects without repeating writes. The toolkit, requiring Python 3.11 or newer, measures whether coding agents can find instructions, recover from ambiguous responses, and have their success claims independently verified.

read2 min views3 publishedAug 28, 2026
Testing Agent Experience in Agent-Native Dev Tools
Image: Michielbdejong (auto-discovered)

Measure whether developer tools are understandable, recoverable, and verifiable for coding agents.

DevTool AX Kit is a small, local-first toolkit for testing Agent-Native developer tools. It captures what happened, verifies what actually happened, and makes ambiguous external effects safe to inspect without repeating them.

Agent success is more than “the model produced code.” A useful evaluation asks:

  • Could the agent find the right instructions and interfaces?
  • Could it recover after an ambiguous tool response?
  • Did an independent verifier agree with its success claim?
  • Were retries, credentials, and external side effects contained?
Capability Use it to measure
Run capture and snapshots What the agent saw and changed
Checkpoints and pinned replay Whether uncertain work can be resumed safely
Effect receipts Whether an external write is identified and recoverable
Redaction and safety assertions Whether evidence can be shared safely
AX skills and templates How to design, verify, compare, and report tasks

Requires Python 3.11 or newer. No runtime dependencies are required.

git clone https://github.com/shenli/devtool-ax-kit.git
cd devtool-ax-kit
python3 -m unittest discover -s tests -v
python3 scripts/replay_experiment.py
python3 -m agent_run --help

Capture a local command:

python3 -m agent_run capture --workspace /path/to/workspace -- python3 -m unittest

Record a receipted effect, then replay it without executing the write:

python3 -m agent_run record-tool --run RUN_ID \
  --name example.send --input '{"event":"welcome/42"}' \
  --output '{"status":"accepted"}' --effect write \
  --receipt '{"request_id":"demo-123"}' --authoritative-status accepted
python3 -m agent_run checkpoint --run RUN_ID --workspace /path/to/workspace --label after-write
python3 -m agent_run replay --checkpoint CHECKPOINT_ID

Pinned replay returns the original receipt without executing the write; an unrecorded write is rejected.

agent_run/                  capture, snapshots, checkpoints, replay
skills/                     reusable AX evaluation instructions
docs/                       methodology, taxonomy, and report templates
tests/                      local regression tests
scripts/replay_experiment.py synthetic mechanics demonstration

Start with AGENTS.md, then choose the relevant skill under

. The

skills/

documentation indexlinks the methodology and example artifacts.

This is evaluation instrumentation—not a credential vault, sandbox provider, orchestrator, security audit, or exact model-replay system. Keep experiments local or use disposable test resources, and run independent verification outside the agent's editable workspace.

Keep tasks vendor-neutral, verifiers deterministic, and evidence reproducible. Run the unit tests and skill validators before opening a pull request. See SECURITY.md before sharing trajectories or external-run data.

── more in #developer-tools 4 stories · sorted by recency
── more on @shen li 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/testing-agent-experi…] indexed:0 read:2min 2026-08-28 ·