tangle/faster-test-loop
Run the failing test file after each edit. Full suite once before finishing.
Run agents in sandboxes with routing and traces.
Tangle gives developers isolated sandboxes, an agent runtime, model routing, approved integrations, and observability. Build an agent, run it, and inspect its traces before changing its behavior.
Sandbox and Router are live developer entry points. A hospitality guest-request assistant is the first packaged use case, in preview.
Hospitality guest requests are the first hosted assistant preview
This preview aims to turn a guest message into an assigned task and alert a person when work is overdue. The full request-to-resolution flow is still being tested with a design partner. It is a hospitality workflow preview, not a general assistant platform.
Give every agent an isolated workspace.
Coding harnesses, tool-calling agents, long-running workflows: each gets a real computer in a Tangle Sandbox with files, a terminal, and browser access.
$ clauderunning$ codexrunning$ opencoderunning$ hermesrunning$ openclawrunning$ nanoclawrunning$ kimirunning$ pirunningTurn each run into a reviewable record.
Capture the run
Record model calls, tool use, timing, tokens, and cost so a result can be inspected after the agent finishes.
illustrative trace · checkout-agent38.2s
run · fix flaky checkout test38.2s
claude-sonnet-5 · plan2.1s
read · checkout.test.ts0.5s
pnpm test · full suite12.8s
edit · retry-policy.ts1.9s
pnpm test · full suite11.4s
edit · checkout.test.ts0.9s
pnpm test · full suite8.9s
Find what repeats
Analyze multiple runs to find recurring failures and expensive steps worth testing as candidate changes.
illustrative trace · checkout-agent38.2s
run · fix flaky checkout test38.2s
claude-sonnet-5 · plan2.1s
read · checkout.test.ts0.5s
pnpm test · full suite12.8s
edit · retry-policy.ts1.9s
pnpm test · full suite11.4s
edit · checkout.test.ts0.9s
pnpm test · full suite8.9s
Review changes where you work
Turn measured findings into a pull request, issue, skill proposal, or team summary. A person decides what ships.
TAN-312
Adopt the failing-test-first loop across all coding agents.
skills/testing.md
Proposed testing guidance is ready for review.
summary
Candidate passed the selected cases; review the results before rollout.
Infrastructure for each agent run.
The five layers are sandbox, runtime, router, integrations, and observability.Sandbox andRouter have live developer entry points. Runtime executes agent profiles in sandboxes. Integrations connect approved external services through grants.Intelligence is the hosted dashboard for agent traces. Send traces through OpenTelemetry or a Tangle SDK, or run an agent in Sandbox to record its work there.
Sandboxes
Isolated computers for agents: shell, files, browser, any coding harness.
sandbox.tangle.toolsIntelligence
Analyze traces and compare candidate changes against held-out cases.
intelligence.tangle.toolsRouter
OpenAI-compatible access to multiple model providers through one API.
router.tangle.toolsSimple, usage-based pricing.
Start free. Every plan includes monthly credit and pays the same per-second compute rates.
Free
$0/mo
Get started with Tangle.- $2 in monthly credit
- 1 concurrent sandbox
- 60 requests/minute
- Community support
RecommendedPro
$29/mo
Production usage for individuals and small teams.- $30 in monthly credit
- 25 concurrent sandboxes
- 300 requests/minute
- Overage at the same per-second rates
- Priority scheduling
Enterprise
$99/mo
High-scale workloads and dedicated support.- $120 in monthly credit
- Unlimited concurrent sandboxes
- Discounted compute rates
- 1000 requests/minute
- Dedicated support
Billed at id.tangle.tools. One key for inference, compute, and intelligence. Ask about Enterprise support and availability at [email protected].