Yearly running cost Assuming 1,200 project packs a year
By hand $108K / year 1,800 hours of work
Subscription n.a.
This workflow $117 / year Machine usage only; setup, hosting and review are extra. Which evidence should it prepare? Turn engineering records into source-linked project narratives and time-allocation drafts for your tax adviser.
One project pack includes up to 100 engineering records.
Review from exports Project evidence pack $1,152 – 3,360 setup Read-only engineering sync Add an authorized system connection $1,440 – 4,320 setup
Which system should it connect to?Jira Linear GitHub metadata No source code collection, eligibility decisions or tax filing. Your tax adviser approves narratives and allocations.
What is included Use ticket exports, commit metadata and agreed project mappings. Time allocations are drafts, not proof of hours worked. Missing evidence stays visible rather than being invented.
Use ticket exports, commit metadata and agreed project mappings. Time allocations are drafts, not proof of hours worked. Missing evidence stays visible rather than being invented.
Claim scope: up to 1 adviser-approved jurisdiction and period.
Model input budget: up to 16,000 tokens across the reference run.
Model output budget: up to 2,200 tokens across the reference run.
Standard independent test set: at least 100 project packs.
Strict independent test set: at least 200 project packs.
Reference application CPU: 2 cores.
Reference application memory: 4 GB.
What standard do you need? Choose the acceptance targets your provider must demonstrate on your own test material.
Standard Test the defined workload and controls. Source-linked statements: ≥98% Relevant records included: ≥95% Included Strict Tighter targets and a larger independent test set. Source-linked statements: ≥99% Relevant records included: ≥98% Setup +$360 – 1,200 My own requirements Agree different targets and scope with your provider. Quote separately
How these standards are measured Hold out complete projects and claim periods, including shared contributors, duplicated tickets, missing dates and projects with no qualifying evidence. Agree the holdout set before tuning. Report each metric with its numerator, denominator and exclusions; abstentions count against coverage. Test all inputs, including failures, rather than only accepted results.
Targets for your selected standard What is checked Target Source-linked statementsSupported factual statements divided by all factual statements in delivered narratives; missing or incorrect citations fail. ≥98% Relevant records includedRelevant records represented divided by all relevant records in an independently labeled project pack. ≥95% Correct allocation calculationsCorrect contributor-period totals divided by all required totals; overlapping assignments must not double-count time. ≥99% Approval and data controlsPassed control cases divided by all independently tested unauthorized-action, stale-input and sensitive-data cases; any critical failure rejects delivery. ≥100%
Targets apply to the agreed independent test set, not every possible future input. During the pilot, a person reviews every result. Any unauthorized action or sensitive-data exposure fails acceptance.
How quickly do you need each project pack? Choose the time from accepted input to a reviewable project pack. Human review and waiting for source access are separate.
Within 3 minutes Included Within 2 minutes Setup +$144 – 480 Within 60 seconds Setup +$288 – 840
Timing details Measure wall-clock time including queueing, model calls, validation and permitted retries. Report failures and deadline misses. Faster targets need pilot testing; they are not vendor benchmarks.
The target applies to at least 95% of agreed test runs, with 1 in progress at a time.
How much should each project pack cost? Choose a machine-cost target per project pack. A lower cap may limit model calls and iterations.
Up to $1.00 Included Up to $0.75 Setup +$144 – 480 Up to $0.50 Setup +$288 – 840
Cost details Includes reference model usage, a retry allowance and allocated hosting at the stated volume. Human review, source-system subscriptions and paid connector access are separate. A tighter target must preserve the selected standards in the pilot.
Reference machine cost: $0.40 – 0.70 per project pack at 100 project packs a month. The selected cap is a target to test, not a replacement for this estimate.
Where do you want it to run? Run the workflow in your cloud or on your own machine. Choose separately whether it may use an external AI model.
Run it onYour cloud Local environment AI model accessApproved model API No external model calls
Data and access details Run in your controlled cloud environment with scoped access and retained review records.
Use an approved external model with the agreed data-processing terms and minimum necessary input.
Local hosting does not itself keep data offline. Connected business systems may still use the network. Private inference needs suitable hardware and a separate measured running cost; access and retention rules must be agreed before real data is used.
How do you want to use it? Choose a browser interface, an MCP tool for your current agent, or a standalone agent.
Web page Review each project pack in a private browser interface. Included Your AI agent Call the workflow through MCP; the same access and approval rules apply. Setup +$72 – 360 Standalone agent Use a dedicated agent with the agreed triggers and controls. Setup +$144 – 480