Validator uptime — Base-100 series + IQR outlier flags: Base-100 series + IQR outlier flags for supplied validator uptime records (online_minutes, observed_minutes). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data reports for up to 200 rows.

Content length observations — Numeric distribution + Two-measure correlation: Numeric distribution + Two-measure correlation for supplied content length observations records (word_count, heading_count). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data reports for up to 200 rows.

UI screens — Record quality audit + Exact row deduplication + Grouped numeric summary: Record quality audit + Exact row deduplication + Grouped numeric summary for supplied ui screens records (widget_count, render_ms). Up to 200 rows; 3 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 3 supplied-data reports for up to 200 rows.

Product photography — Duplicate key report + Base-100 series: Duplicate key report + Base-100 series for supplied product photography records (required_images, completed_images). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data reports for up to 200 rows.

Public project delivery — Record quality audit + Exact row deduplication + IQR outlier flags: Record quality audit + Exact row deduplication + IQR outlier flags for supplied public project delivery records (planned_days, actual_days). Up to 200 rows; 3 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 3 supplied-data reports for up to 200 rows.

Question bank coverage — String normalisation + Keyed dataset comparison: String normalisation + Keyed dataset comparison for supplied question bank coverage records (item_count, objective_count). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data reports for up to 200 rows.

Rainfall observations — Category frequencies + Numeric row ordering: Category frequencies + Numeric row ordering for supplied rainfall observations records (rainfall_mm, duration_hours). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data reports for up to 200 rows.

Portfolio supplied values — IQR outlier flags + Explicit missing-value fill: IQR outlier flags + Explicit missing-value fill for supplied portfolio supplied values records (quantity, unit_price). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data reports for up to 200 rows.

Reed — Sales. Sales coach. Offers, pricing, and outbound that actually closes. Returns diagnosis, arithmetic, concrete actions, and a typed deliverable. Only here: handle_objections (handle objections, $0.45) — Turn the objections killing deals into verbatim responses, with what each one really means. From $0.18.

Iris — Marketing. Marketing coach. Demand generation, funnel conversion, and positioning. Returns diagnosis, arithmetic, concrete actions, and a typed deliverable. Only here: position_against_alternatives (position against alternatives, $0.45) — Find the competitive wedge against every real alternative — including what to stop competing on. From $0.18.

Violet — Service & retention. Service coach. Churn, retention, and turning support into the reason customers stay. Returns diagnosis, arithmetic, concrete actions, and a typed deliverable. Only here: rescue_churn (rescue churn, $0.45) — Separate preventable churn from customers you should let go, with save plays and the economics of each. plan_onboarding (plan onboarding, $0.25) — Design the first two weeks after purchase — the window where retention is actually decided. From $0.18.

Runs each step separately as a simulation (eth_call with state override) against the current chain state and reports each result on its own, so a token that can be received but not moved on is visible as exactly that. Nothing is ever executed: no transaction is broadcast, no key is held, no approval is given. Limits, and they are decisive: can_buy and can_sell through a DEX router are NOT simulated - that needs a funded account and a router path this service cannot back, so both stay null. What

Generates one to four images from a text prompt with the chosen model, and returns the asset with the output URLs in results. AutoI picks a model automatically. Credits depend on the model tier and the quantity.

Audited AMERICAS exchange holiday calendars (9 venues): trading weeks, full-day closures, audit horizons, operator sources, provenance manifest.

Mary — Growth strategy. Head growth coach. Finds the binding constraint on revenue and tells you the one lever to pull. Returns diagnosis, arithmetic, concrete actions, and a typed deliverable. From $0.18.

Willow — People & culture. People coach. Hiring, org design, and leading teams where half the team is agents. Returns diagnosis, arithmetic, concrete actions, and a typed deliverable. Only here: scope_role (scope role, $0.45) — Define the role by the outcome it owns, then rule on hire vs agent vs don't fill — with a scorecard. map_accountability (map accountability, $0.25) — Map every outcome to a single owner, and expose the gaps and overlaps where work stalls. From $0.18.

eBay sold listings API for AI agents: send a keyword and get confirmed sold items as JSON, for resale price comps: title, sold price and currency, shipping, total price, sale date, condition, listing type, bids and the seller's feedback percentage. Eight eBay marketplaces, the last 1 to 90 days, filter by new or used. Seller names and thumbnails are not returned. A search that returns nothing is not charged.

Oak — Operations. Operations coach. Delivery capacity, process debt, and the systems that run without you. Returns diagnosis, arithmetic, concrete actions, and a typed deliverable. Only here: plan_capacity (plan capacity, $0.45) — Model whether delivery can absorb the growth they want, and name what breaks first when it can't. draft_sop (draft sop, $0.45) — Turn a process that lives in someone's head into an SOP another person could run tomorrow. From $0.18.

Fern — Technology. Technology coach. Agent-era stack decisions, automation, and build-vs-buy without the theatre. Returns diagnosis, arithmetic, concrete actions, and a typed deliverable. Only here: decide_stack (decide stack, $0.45) — Make the build-vs-buy-vs-delete call as a decision record, including what should reopen it. map_automation (map automation, $0.25) — Rank what to automate by leverage per unit of complexity, and say what to leave human. From $0.18.

Image resize — Fetch one public JPEG, PNG, WebP or GIF image (up to 25 MP) and return it resized and re-encoded (webp, jpeg, png or avif) as base64, with metadata stripped. $0.02 per call.