# Edxperimental Labs Studio Catalog Generated product shelf for demos, buyer follow-up, and consulting handoff. Product count: 8 Demo-ready count: 7 ## Agent Benchmark Explorer Stage: Preview Audience: AI teams comparing autonomous workflows Summary: A structured benchmark surface for measuring whether agents can plan, use tools, recover from errors, and complete useful work rather than only answer prompts. Maturity: Can be shown as a product demo today Demo readiness: 76/100 Missing for live demo: - Reviewer-signed trace - Real screenshot/media - Provider or agent export Buyer questions: - Can the agent recover after a bad tool call? - Does it verify state before claiming completion? - How much does each accepted workflow actually cost? - Which failures should trigger human handoff? Outputs: - Agent scorecard - Trace review table - Failure taxonomy - Cost per resolved task Links: [Product page](/studio/agent-benchmark-explorer) / [JSON packet](/reports/studio/agent-benchmark-explorer.json) Preview: /reports/studio/previews/agent-benchmark-explorer.png ## Coding Agent Arena Stage: Research Audience: Engineering leaders and founders Summary: A coding-agent evaluation track for repository edits, bug fixes, browser checks, terminal usage, and regression discipline. Maturity: Research surface ready for benchmark-backed demos Demo readiness: 82/100 Missing for live demo: - Product walkthrough video - Client-approved example - Real run export Buyer questions: - Can this agent work inside our existing codebase? - Does it respect ownership boundaries and avoid unrelated churn? - Can it debug failing tests without hiding the failure? - What tasks are safe to delegate today? Outputs: - Patch review - Regression report - Tool-use transcript - Merge-readiness score Links: [Product page](/studio/coding-agent-arena) / [JSON packet](/reports/studio/coding-agent-arena.json) Preview: /reports/studio/previews/coding-agent-arena.png ## Browser Agent Evaluation Kit Stage: Research Audience: Teams automating web operations Summary: Browser-agent tasks for navigation, form filling, extraction, screenshot QA, and resilient recovery from UI changes. Maturity: Research surface ready for benchmark-backed demos Demo readiness: 64/100 Missing for live demo: - Reviewer-signed trace - Real screenshot/media - Provider or agent export Buyer questions: - Can the agent prove the page reached the right state? - What happens when a modal or validation error appears? - Which workflows are stable enough for automation? - Where should a human remain in the loop? Outputs: - Browser task report - Screenshot evidence - Selector fragility map - Handoff recommendation Links: [Product page](/studio/browser-agent-evaluation-kit) / [JSON packet](/reports/studio/browser-agent-evaluation-kit.json) Preview: /reports/studio/previews/browser-agent-evaluation-kit.png ## Customer Support Agent Scorecard Stage: Consulting Audience: Support, CX, and operations teams Summary: A scorecard for support agents covering escalation quality, policy adherence, multilingual handling, hallucination risk, and customer outcome. Maturity: Best introduced inside a consulting conversation Demo readiness: 82/100 Missing for live demo: - Product walkthrough video - Client-approved example - Real run export Buyer questions: - Will the agent respect our refund and exception policy? - Can it handle bilingual or region-specific context? - When should it escalate instead of improvising? - Which support queues should be automated first? Outputs: - Support scenario pack - Policy adherence matrix - Escalation audit - Rollout recommendation Links: [Product page](/studio/customer-support-agent-scorecard) / [JSON packet](/reports/studio/customer-support-agent-scorecard.json) Preview: /reports/studio/previews/customer-support-agent-scorecard.png ## Indian Workflow Benchmark Stage: Designing v0.1 Audience: Indian enterprises, AI buyers, and product teams Summary: A workflow benchmark for Indian business tasks: finance, support, multilingual handoffs, document reasoning, sales ops, and evidence-grounded escalation. Maturity: Research surface ready for benchmark-backed demos Demo readiness: 82/100 Missing for live demo: - Product walkthrough video - Client-approved example - Real run export Buyer questions: - Which models survive Indian document and support workflows? - Where do multilingual or policy tasks fail? - What can be safely automated versus escalated? - How do quality, latency, and cost change by workflow type? Outputs: - Workflow task pack - Model comparison memo - Evidence audit - Deployment readiness map Links: [Product page](/studio/indian-workflow-benchmark) / [JSON packet](/reports/studio/indian-workflow-benchmark.json) Preview: /reports/studio/previews/indian-workflow-benchmark.png ## Model Recommendation Console Stage: Preview Audience: Buyers choosing models or API providers Summary: A decision console that maps use-case constraints to a model shortlist across quality, latency, price, context, privacy, and deployment surface. Maturity: Can be shown as a product demo today Demo readiness: 82/100 Missing for live demo: - Product walkthrough video - Client-approved example - Real run export Buyer questions: - Which model should handle the expensive path? - Where can a cheaper router or fallback be used? - What latency and privacy constraints change the answer? - What benchmark evidence is still missing? Outputs: - Model shortlist - Fallback map - Monthly cost envelope - Pre-production test plan Links: [Product page](/studio/model-recommendation-console) / [JSON packet](/reports/studio/model-recommendation-console.json) Preview: /reports/studio/previews/model-recommendation-console.png ## Cost Curve Workbench Stage: Preview Audience: Finance and platform teams Summary: A calculator-style tool for converting token pricing into workload cost curves, batch discounts, cache effects, and per-resolution economics. Maturity: Can be shown as a product demo today Demo readiness: 82/100 Missing for live demo: - Product walkthrough video - Client-approved example - Real run export Buyer questions: - What will this cost at 10k, 100k, or 1M workflows? - How much do retries and human review change the answer? - When does prompt caching materially matter? - Which model class is cheap after quality is included? Outputs: - Cost curve - Scenario table - Savings waterfall - Budget envelope Links: [Product page](/studio/cost-curve-workbench) / [JSON packet](/reports/studio/cost-curve-workbench.json) Preview: /reports/studio/previews/cost-curve-workbench.png ## Consulting Diagnostic Stage: Client intake Audience: Founders, AI buyers, and operations leaders Summary: A fast intake surface for turning an AI idea, vendor claim, or production concern into a benchmarkable consulting engagement. Maturity: Research surface ready for benchmark-backed demos Demo readiness: 82/100 Missing for live demo: - Product walkthrough video - Client-approved example - Real run export Buyer questions: - What is the smallest benchmark we should run first? - Which evidence is missing before production? - Who should own the technical and sales-engineering handoff? - How quickly can we get a decision artifact? Outputs: - Diagnostic memo - Evidence request list - First-sprint plan - Owner handoff Links: [Product page](/studio/consulting-diagnostic) / [JSON packet](/reports/studio/consulting-diagnostic.json) Preview: /reports/studio/previews/consulting-diagnostic.png