← Aiske.ai AI Portal

Product & Technology
14-Day AI Usage Outcomes

How Product & Technology used AI across everything we shipped in the last 14 days — cross-referencing Jira (source of truth for what we worked on) against Claude Code telemetry, GitHub, Confluence and Slack.

Window: 2026-06-16 → 2026-06-30 Generated 2026-06-30 Regenerated each run
Capacity gained · last 14 days
~130 engineering hours gained
AI didn't replace anyone - this fortnight it handed the Product & Technology function about 130 hours back from boilerplate and repetitive work (~16 developer-days), freeing our 14 active engineers to spend more time on the hard, creative problems only people can solve. Same function - more shipped.
Amplified, not replaced. AI clears the busywork so our people spend their time on the work that genuinely needs a human.
~130
Hours gained (fortnight)
~16
Developer-days
14
Active AI developers
~3,382 hrs
Annualised run-rate
Backend & data services ~78hAI code-review on PRs ~30hAI-drafted specs & tickets ~22h
Estimate from our AI cost-benefit model (37% of work AI-assisted x 25% average gain), prorated to the 14 developers active in Claude Code on company repositories this fortnight (a tiered 2,899 hrs/yr at 12 devs, scaled to 14 and to a 14-day window). An estimate, not a timesheet.

01At a glance


15
Projects active
1,070
Issues worked
482
Resolved
45
People
5.92B
AI tokens (14d)
137,412
AI lines of code
265
AI sessions
14
Active AI devs

Jira is the source of truth (last 14 days, 16-30 June). Claude Code tokens are scoped to company repositories: 5.92B of 17.12B total Claude Code tokens (35%) were on company repos - the rest is planning, research, POCs (marketplace/Cowork) and analysis. Spend is never shown.

02What we worked on (Jira)


Jira is the source of truth. Below: where the work landed and the mix of work types across all active projects in the window. The hatched (diagonal-slash) part of each project bar marks the issues that involved AI (estimated from the project's AI-coding signal).

Activity by project — AI-involved issues hatched
Work-type mix
ProjectFocusIssuesAI coding signal
QAFNDNQA: Foundation (FNDN)467Partial
FITFoundation & Integration134Strong
FARMFarm And Ranch Management132Strong
CSCustomer Support78Partial
DPData Platform76Strong
PSProduction Support37Partial
INFRAInfrastructure - DevOps & Infra36Strong
RNDResearch & Development30Partial
PRDProduct Operations29Partial
QACEXQA: Cattle Experience (CEX)13Partial
TEMTempo13None
ARAccess Requests13None
TAGSTagging Development9Partial
GRASGrassland & Environmental Mgmt2None
DDAData & Analytics1Strong

03How AI was used across the lifecycle


AI is now applied at every stage of delivery. The colour bar shows how well each stage is currently supported — green is well-covered, amber is partial and an opportunity.

Requirements
AI-generated tickets & PRDs
37 epics active across FARM/FIT/DP/INFRA
Design
Claude design mock-ups
9 Design issues + claude.ai/design links in tickets
Spec & QA plan
AI Blast-Radius + test-case generation
Confluence BRT1 not re-pulled this run
Code + tests
Claude Code in company repos
5.92B scoped tokens - 137,412 LOC - 265 sessions
Code review
airbug AI review bot on backend PRs
60 AI-created PRs in window
Testing
AI-maintained E2E specs
324 test executions + 166 test plans (QA Foundation) - mostly manual

04AI coding telemetry


Measured Claude Code usage over the last 14 days (Honeycomb OpenTelemetry), scoped to sessions that edited files in a recognised Aiske.ai repository — i.e. real Jira/GitHub project work. Planning, research, agentic exploration, Cowork POCs and analysis are excluded. All figures are for the window only — not cumulative over the full codebase or all time.

Where AI tokens went (millions)
AI coding by team (tokens, billions)
AI-written lines of code by repository (14 days)
AI-created PRs by repository (14 days)
TeamFocusTokens (company repos)Lines of codeWhat AI is used for
Architecture & DevSecOpsBackend services, MuleSoft/iPaaS integrations & the AI code-review pipeline1.86B35,631Backend services, MuleSoft/iPaaS integrations & the AI code-review pipeline (1 active dev)
Foundations & DevSecOpsMission Control, infrastructure/DevOps, platform & shared services1.73B48,245Mission Control, infrastructure/DevOps, platform & shared services (5 active devs)
Data & IntelligenceDatalake / hwlake-bronze models, lineage catalogue & data pipelines1.34B29,315Datalake / hwlake-bronze models, lineage catalogue & data pipelines (2 active devs)
Core SolutionsFARM & Aiske features, mobile app, tests and the AI part of the app0.96B24,139FARM & Aiske features, mobile app, tests and the AI part of the app (4 active devs)
Product Delivery (direct)Cross-team product delivery & tooling0.03B0Cross-team product delivery & tooling (1 active dev)
Network & IntegrationsIntegration engineering & connectors0.00B82Integration engineering & connectors (1 active dev)

05Highlighted epics & how AI shaped them


EpicProjectHow AI was usedStatus note
FIT-8530 Regression 99.0.0FITcode + specsTo Do
DP-964 Star ranking, Dashboards, Superset clean upDPcode + specsTo Do
RND-34 Integration Unification: unified ACL + strangler rolloutRNDcode + specsIn Progress
FARM-11863 QA / Farm Assurance Tracker — Automated Eligibility Tracking (All Markets)FARMcode + specsIn Progress
FARM-12136 Aiske 1.5 Weight Upload MVPFARMcode + specsTo Do
FIT-8537 Sync Manager: improve logs, reports and reporting dashboardFITcode + specsIn Progress

06How we can use AI even more


The most important section: concrete, evidence-based moves to push productivity further. Ordered by impact.

Put AI on QA Foundation's manual test load

QA: Foundation (FNDN) was the single busiest project this fortnight - 467 issues, including 324 test executions and 166 test plans, almost all run and maintained by hand. This is the clearest AI win available: have Claude Code maintain Cypress/E2E specs in lockstep with UI copy and auto-draft test executions from each test plan. Testing is the weakest AI-assisted stage in our lifecycle strip.

Impact: HighEffort: Medium

Bring Core Solutions back onto tracked-repo AI work

FARM and FIT together carried 266 Jira issues, yet Core Solutions logged the lowest scoped Claude Code usage of any engineering team (0.96B tokens, 4 active devs) - and a chunk of the team's fortnight went into a marketplace/Cowork POC that sits outside our tracked repositories. Redirect that momentum onto FARM/FIT tickets in ngx-app and de-svc-herdchat, and pair the team's heaviest adopter with the lighter ones on real tickets.

Impact: HighEffort: Low

Extend AI beyond code into CS, PS and Product Ops

Customer Support (78), Production Support (37) and Product Operations (29) generated real Jira volume this fortnight but show little to no AI-coding signal because the work is triage, reproduction and comms rather than commits. Give these teams AI templates for ticket triage, reproduction summaries and first-draft customer-facing notes so the assist shows up where the work actually is.

Impact: MediumEffort: Low

Close the P&T adoption gap

Only 14 developers were active in Claude Code on company repositories this fortnight, against a larger P&T engineering headcount. Two teams (Network & Integrations, Product Delivery direct) each had a single, very light active user. Use the leaderboard to name who sits at levels 1-3 and pair them with the four heaviest adopters on live tickets.

Impact: HighEffort: Low

Surface Network & Integrations' iPaaS work

The iot-svc-ipaas repository accounted for ~21% of AI-written lines and a fifth of AI-created PRs this fortnight, but the Network & Integrations team reads as a single near-silent user - the integration work is being credited elsewhere. Confirm sign-in/repo attribution for that team so their genuine AI contribution is visible and they get proper coaching.

Impact: MediumEffort: Low

Standardise Co-Authored-By: Claude on AI-assisted PRs

We saw ~60 AI-created PRs in the window (Mission Control and aiske-infra led), but squash-merges drop the trailer so GitHub attribution under-reads. A commit-hook that preserves the trailer makes AI contribution measurable without changing how anyone works - and lets us tie PR-level AI use back to Jira.

Impact: MediumEffort: Low

Template the repeatable backend & data work

Backend and data services (iot-svc-ipaas, dp-svc-hwlake-bronze, de-svc-herdchat) produced the bulk of AI-written lines this fortnight, and several epics (DP-964 dashboards clean-up, RND-34 integration unification, FIT-8537 sync-manager reporting) are clearly phase-based. Scaffold phase 2/3 off phase 1 and reuse the patterns across DP/FIT/INFRA rather than re-deriving them each time.

Impact: MediumEffort: Medium

Auto-generate release notes & specs from active epics

With 37 epics active this fortnight, generate first-draft release comms and PRDs from each epic and its child issues - especially the customer-visible FARM work (FARM-11863 eligibility tracking, FARM-12136 Aiske 1.5 weight upload). It turns work we already tracked in Jira into shippable communication with almost no extra effort.

Impact: MediumEffort: Low

07Method & caveats


Sources: Jira (REST API, 16-30 June 2026, full paging), Honeycomb Claude Code OTel (company-scoped), GitHub / airbug AI review, AI cost-benefit model (Outcome estimate).

Aiske.ai — Internal & confidential. Generated by the pt-ai-usage-report skill, a companion to the AI Adoption Leaderboard. Figures are decision-support; AI-coding telemetry covers opted-in Claude Code users. Irish/UK spelling throughout.