Dashboard
| Follow-ups per rep / week | Watch | $292.87 |
| Median first-response time | +$927.60 |
| Ticket deflection rate | +$543.80 |
| Time to first follow-up | +$196.03 |
Your top ideas
- Friendly payment reminders
- Draft replies to common customer questions
- Turn job notes into a polished quote
2 ideas in progress · 1 check-in due
Best so far: Friendly payment reminders — Invoices more than 30 days late -38.5%
Fewer than 3 check-ins so far — it is too early to read much into this.
Get your own AI planNew to AI: Discovery
Describe your business in your own words and get a personal AI plan: what to try first, what it could save you, and how to track it.
OpenAI Readiness Scorecard
Score your readiness to invest in AI across five dimensions, find the one thing actually holding you back, and get a dated 90-day plan to fix it.
OpenBuild vs Buy vs Subscribe Advisor
For one use case: build it on the API, buy a vertical SaaS tool, or just buy seats of a general assistant? See the real 3-year cost of each before you decide.
OpenFirst 90 Days AI Plan Generator
Turn a decision into a dated, owned, week-by-week 90-day plan — with go/no-go gates and a calendar export.
OpenAI Opportunity Finder
Describe your business and get a ranked, costed shortlist of AI opportunities — with one clear place to start.
OpenProcess Cost Baseline Calculator
Find out what a manual process really costs you today — the number every AI ROI claim has to beat.
OpenAI Subscription Sprawl Auditor
Find out what you are really spending on AI tools, where it overlaps, and what you could safely cancel.
OpenAI Budget Guardrail Builder
Turn a monthly AI budget into concrete alert thresholds, a forecast-based early warning rule, and an escalation ladder with named roles.
OpenAI Cost Estimator Also listed under For Builders
See what your AI feature could cost each month. Describe the work in your own words — no AI expertise needed.
OpenModel Picker Also listed under For Builders
Which AI model should you use? Answer a few questions and get a transparent, explainable recommendation across Claude, GPT, and Gemini.
OpenROI & Payback Simulator
Find out when an AI project pays for itself — and what happens if your assumptions are wrong.
OpenROI Use Case Builder
Turn a growth goal, customer opportunity, or operating challenge into a practical AI use case with measurable value.
OpenTrue TCO Calculator
API token cost is typically 20-40% of the real cost of running an AI feature. This tool computes the rest.
OpenAI Risk Assessment Generator
Turn a description of an AI system into a structured risk assessment — suggested tier, risks, mitigations, and a monitoring plan.
OpenAI Usage Policy Generator
Generate a practical internal AI usage policy your employees will actually follow.
OpenVendor AI Due Diligence Questionnaire Generator
Turn a vendor pitch into the questions you should ask before you buy — with the answer you want and the answer that should worry you.
OpenBatch API Suitability Checker
Describe a workload and get a plain verdict on whether it fits the Batch API — suitable, partially suitable, or not — with the dollar saving and the queue-time trade-off.
OpenContext Window Budget Planner
See exactly what fills up a model's context window each turn, the headroom you actually have, and why a chat session's cost grows the way it does.
OpenCost-Aware Routing Designer
Design a cheap-model-first cascade for a workload, price it honestly against just using your strong model, and get the break-even escalation rate before you build anything.
OpenAI Cost Estimator Also listed under For Leaders
See what your AI feature could cost each month. Describe the work in your own words — no AI expertise needed.
OpenModel Picker Also listed under For Leaders
Which AI model should you use? Answer a few questions and get a transparent, explainable recommendation across Claude, GPT, and Gemini.
OpenPrompt Caching Savings Analyzer
Paste a prompt and see exactly what restructuring it for caching would save — and the call volume below which caching costs more than it saves.
OpenRate Limit & Capacity Planner
See your projected peak traffic against your actual rate limits, how long until you hit them, and exactly what to change before you do.
OpenToken Counter
Count real tokens for your text, per Claude model — different models tokenize differently.
OpenCLAUDE.md Generator
Generate a tailored CLAUDE.md for your project in under a minute.
OpenFew-Shot Example Set Builder
Get the smallest, most diverse example set that actually earns its keep — priced per call and per month, with an honest verdict on whether a better instruction would do instead.
OpenMCP Config Wizard
Build a valid claude_desktop_config.json or .mcp.json in a few clicks — no hand-written JSON.
OpenSystem Prompt Generator
Turn a description of what an AI feature should do into a structured, cacheable, production-ready system prompt.
OpenPrompt Optimizer
Rewrite a system prompt shorter at equal or better quality, with a real token delta, a real dollar saving, and an honest list of what might change.
OpenRAG Chunking & Retrieval Planner
Get a chunk size, overlap, and top-k with the reasoning behind each, priced end to end — and an honest check against just putting the whole corpus in context with caching.
OpenReAct Prompt Converter
Turn a plain prompt into a ReAct reasoning loop — and see what the loop will actually cost before you run it.
OpenSkill File Generator
Generate a SKILL.md with a description that triggers at the right moments — and never at the wrong ones.
OpenStructured Output Schema Builder
Turn a plain-language field list into a JSON Schema, a prompt fragment, real validation code, a repair prompt for drift, and edge-case test inputs — plus a warning when the shape itself is the reliability risk.
OpenSubagent & Slash Command Generator
Generate a ready-to-save Claude Code subagent or slash command, with a least-privilege tool list, explained and warned on where it's broad.
OpenTool / Function Schema Generator
Turn a plain-language tool description into a valid schema — with the "when NOT to use this" clause that's usually missing, error-shape guidance, and trigger test cases.
OpenWorkflow to Agent Blueprint
Turn a described manual process into a structured blueprint: what to automate, what to keep human, failure handling, real cost, and a phased build plan.
OpenCLAUDE.md Auditor
Score your CLAUDE.md on actionability, hard rules, signal density, completeness, and agent ergonomics.
OpenEval Set Generator
Turn a feature description into a starter eval set: concrete test cases, a grading rubric, and a pass bar.
OpenEval Runner
Run a saved eval set against one or more models and get a scorecard: pass rate, cost, and latency — with evidence, not vibes.
OpenGolden Dataset Manager
Curate, version, and review your test cases as a first-class asset — the substrate the Eval Runner, Prompt Regression Diff, and Blast Radius all run against.
OpenGrounding / Hallucination Checker
Check a generated output against its source document, claim by claim — supported, unsupported, or contradicted.
OpenLLM-Judge Calibrator
Compare judge verdicts against human labels and find out whether you can trust automated grading — agreement rate, Cohen's kappa, bias checks, and a concrete recommendation.
OpenPrompt Auditor
Score your system prompt on structure, specificity, edge cases, token efficiency, and cacheability.
OpenPrompt Injection & Red-Team Tester
Find out whether your prompt or agent can be manipulated — before a customer does.
OpenPrompt Regression Diff
Prove a prompt change didn't break anything before it ships — run both versions against the same eval set and see what changed.
OpenSkill Auditor
Score your SKILL.md on trigger precision, instruction completeness, output contract, and scope discipline.
OpenAgent Trace Analyzer
Paste an agent trace and find the loops, retries, and discarded work that quietly inflate your AI bill.
OpenData Handling & Redaction Advisor
Find out which data can go to which AI model or provider — and get the redaction rules for the rest.
OpenAI Incident Response Runbook Generator
Get a runbook for the moment your AI system leaks data, hallucinates into production, or the bill spikes — before you need it.
Open| Hypothesis | KPIs | Created | |
|---|---|---|---|
|
Support deflection with an AI assistant
We believe that drafting first replies to support tickets with an AI assistant for our support team will reduce average first-response time this quarter.
|
2 | Sep 7, 2026 | Manage KPIs |
|
Faster sales follow-ups with Claude
We believe that drafting follow-up emails with Claude for the sales team will speed up time to first follow-up within 8 weeks.
|
2 | Sep 24, 2026 | Manage KPIs |
- CLAUDE.md — Acme Support Bot v2 · Nov 2
- Ticket Triage Skill v1 · Oct 29
- Support Bot $62.10
- Batch jobs $52.00
- workspace ws_internal_tools $41.70
| Provider | USD | Share |
|---|---|---|
| Anthropic | $1,132.86 | 72% |
| OpenAI | $430.81 | 28% |
| What | Provider | Amount |
|---|---|---|
| Images | OpenAI | 1,240 images |
| Speech to text | OpenAI | 18,400 seconds of audio |
| File storage for search | OpenAI | 2.00 GB stored (latest day) |
Anthropic detail
Cost types, service tiers, context windows, processing location, fast mode, rate limits and per-key estimates come from fields only Anthropic's reports include — your other providers' usage isn't part of these views.| Type | USD |
|---|---|
uncached_input_tokens |
$475.80 |
output_tokens |
$521.12 |
cache_read_input_tokens |
$79.30 |
cache_creation_input_tokens |
$56.64 |
| Tier | Tokens |
|---|---|
| standard | 17,546,188 |
| batch | 3,851,602 |
| Context window | Tokens |
|---|---|
| 200k | 15,192,431 |
| 1M | 6,205,359 |
| Geo | Tokens |
|---|---|
| not_available (pre-Feb-2026 models) | 11,768,785 |
| us | 9,629,005 |
| Speed | Tokens |
|---|---|
| standard | 19,258,011 |
| fast | 2,139,779 |
| Group | Models | Input/min | Peak in | Input % | Output/min | Peak out | Output % | Req/min |
|---|---|---|---|---|---|---|---|---|
| model_group | 3 models | 2,000,000 | 1,362,000 | 68.1% | 400,000 | 208,000 | 52.0% | 4,000 |
| API key | Hint | Workspace | Tokens | Est. cost |
|---|---|---|---|---|
| Production key | sk-ant-…a1b2 |
Production | 12,410,718 | $648.20 |
| Support bot key | sk-ant-…9f7c |
Support Bot | 6,633,315 | $351.33 |
| Batch jobs key | sk-ant-…44de |
Production | 2,353,757 | $86.71 |