Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.roboticks.io/llms.txt

Use this file to discover all available pages before exploring further.

​
AI features

Roboticks runs Anthropic Claude on AWS Bedrock behind a small set of typed task definitions. Every AI surface in the product maps to one AITaskType with a fixed model, fixed input/output window, and a fixed token_cost — so plan gating is deterministic and the surface area is auditable.
The customer never picks the model. The backend picks Haiku, Sonnet, or Opus per task. Bills count against the org’s monthly ai_tokens grant; overage stops at the plan ceiling unless the org has a top-up. See Pricing → AI tokens for the unit economics.

​
Where AI shows up

SurfaceUI entry pointDoc page
Test failure triageRun-detail page → AI Triage panelTest debugging
Test-run analysisRun-detail page → AI AnalyzeTest debugging
Test flakinessTest case page → Flakiness dialogTest debugging
Sim-vs-real comparisonRun-detail page (sim run) → Compare RealTest debugging
Inline log anomaliesLogs page → highlighted linesTest debugging
Requirement qualityRequirement detail → Quality cardRequirements & traceability
Verification methodRequirement detail → Verification cardRequirements & traceability
Duplicate / contradictionRequirement detail → Duplicates cardRequirements & traceability
Standards clause linkageRequirement detail → Standards cardRequirements & traceability
Chat with requirements docRequirements upload page → chat dockRequirements & traceability
Test suggestions for uncovered reqTraceability gaps → AI SuggestRequirements & traceability
Gap explanationTraceability matrix → uncovered rowRequirements & traceability
Evidence-pack narrativeEvidence pack detail → Generate narrativeEvidence & standards
Pre-audit Q&AEvidence pack detail → AskEvidence & standards
Pack completeness gateEvidence pack detail → CompletenessEvidence & standards
Standards coverage deltaStandard detail → Coverage AIEvidence & standards
Standards clause summaryStandard clause → Plain EnglishEvidence & standards
Posture weekly digestPosture dashboard → top bannerEvidence & standards
Natural-language searchGlobal search bar → “Ask” toggleSearch

​
Models and routing

Routing is fixed in app/core/ai_config.py and is not a tunable for customers. The mapping:
TierModelUsed for
Cheap / fastclaude-haiku-4-5Single-requirement quality + verification-method + gap-explain, log summarisation, entity extraction, search query parse, standards clause summary
Defaultclaude-sonnet-4-5Test-failure analysis, test-run analysis, conversation responses, flakiness, requirement generation, duplicate / standards-link, doc chat, evidence pack QA / completeness, standards coverage delta, posture digest
Heavy reasoningclaude-opus-4-5Root-cause analysis, sim-vs-real comparison, evidence-pack narrative
Bedrock model IDs live alongside the routing table; cross-region inference profiles (us.anthropic...) are baked in.

​
How billing works

Each call bills the Bedrock-equivalent token count × 2x margin, with output weighted by the model’s output/input price ratio. So a typical Sonnet request that consumes 5 000 input + 1 000 output tokens at Bedrock prices the customer is charged roughly: 
billable = round(2 × (5 000 + 5 × 1 000)) = 20 000 ai_tokens
The platform never charges by absolute dollars — it charges in units of ai_tokens the customer’s plan ships with monthly. Top-up packs add ai_tokens_prepaid that never expire. For a worst-case ceiling per task — the figure the plan-gate compares against — see max_billable_tokens() in ai_config.py. The Free plan’s 100 000-token grant covers Haiku-tier tasks but is below the worst-case requirement-generation gate, so the heavy AI features are implicitly Team+.

​
What the AI does NOT do

  • It never edits your code, your requirements, your tests, or your evidence packs. Every “AI assist” is a suggestion the engineer accepts or rejects.
  • It never reads your repos directly. AI prompts are built from data already in the platform (test results, requirements text, logs the runner shipped). The hosted MCP server can read more, but only when an LLM calls it through the platform’s billing-and-auth boundary.
  • It never sees a customer’s data outside the Bedrock invocation. Roboticks does not train models. Anthropic does not use Bedrock prompts for training under AWS’s contractual terms.
  • It is not a substitute for the certification auditor. AI assists draft and explain; the engineer signs.

​
Plan gating

PlanMonthly ai_tokens grantEffectively unlocks
Free100 000Haiku-tier surfaces: log summarisation, clause summaries, single-requirement quality / gap-explain
Team5 000 000Everything below worst-case requirement-generation; flakiness; sim-vs-real; evidence narratives at moderate cadence
Enterprise∞All surfaces, no rate cap beyond Bedrock-side limits
Customers can buy top-up packs at any tier; topped-up tokens are ai_tokens_prepaid and never reset.

​
Next

Test debugging

Triage, flakiness, sim-vs-real, log anomalies.

Requirements & traceability

INCOSE quality, verification, duplicates, gaps, doc chat.

Evidence & standards

Pack narrative, pre-audit Q&A, clause summaries.

Natural-language search

Ask questions; get answers grounded in the project’s data.