Personal website and interactive professional story
A rough creative direction can become a tangible web experience, but verification still matters.
Explore related workDivya Does AI · A recurring experiment
What I asked AI to do. What actually happened. What broke. And was it worth managing?
A candid, evolving assessment of using AI as an execution partner across building, writing, research and everyday operations. Not a productivity victory lap.
By Divya Kandikatti · Covers Q3 and Q4 2026 · Published · Updated
The central finding
Our experiments show creative and research leverage, but a recurring gap between useful output and independently verified completion.
Engineering reality / Sep–Nov 2026
Actual GitHub and Vercel activity, not AI self-ratings. These counts represent engineering activity, not independently verified production delivery.
Real delivery activity, but the next question is how many of those PRs produced verified outcomes versus rework.
Source: connected GitHub PR search by creation date (September 1–October 31, 2026) and Vercel deployment list for the main website project queried from September 1 through November 2, 2026. The Vercel query returned 250 records, with the oldest returned deployment on September 14; this is a bounded activity window and must not be interpreted as full Q3 or Q4 totals. Ready ≠ QA passed. Other repositories and projects are not included. Source records were reviewed through authorized private connections; the repository and deployment logs are not publicly accessible. These figures should be treated as a dated research snapshot, not independently public-auditable data.
01 / Collaboration
The first scorecard reflects our conversation-based self-assessment across the wider August–November collaboration. It is not a Q3-only measurement, and should not be compared numerically across quarters yet.
Our principal gap isn't generating solutions. It's finishing independently with trustworthy evidence.
The pattern: ideation and content are stronger than independent QA and reliable end-to-end completion. The scores are editorial judgments; detailed source-backed KPIs are a future iteration.
02 / Portfolio
Examples with an observed outcome
Visibility is not verification. We keep unverified and incomplete work visible rather than treating every activity as success.
A map of selected workstreams, not a claim about time spent or total volume. Tap a category to explore the underlying examples.
A rough creative direction can become a tangible web experience, but verification still matters.
Explore related workProfessional examples require careful confidentiality and source confirmation.
AI helps develop structure; authentic voice needs deliberate human editing.
Explore related workContinuity is useful, but remembered information must not substitute for verified facts.
Examples are selected from our collaboration and may span longer workstreams. Status is conservative: “Observed” does not mean end-to-end externally audited. Private correspondence and client details are intentionally omitted.
03 / Measurement
Instead of inventing time-savings, success rates or ROI, here's the measurement contract for the next review.
Deliverables with evidence and an accepted result
Unit: CountCompleted tasks accepted without corrective rework / audited completed tasks
Unit: %Times the human had to correct, unblock or re-explain
Unit: CountManual baseline effort minus AI supervision, retries and rework
Unit: HoursValid checks passed on the reviewed commit / checks executed
Unit: %Verified delivered changes / deployments
Unit: RatioCorrect audited personal facts / all audited personal facts
Unit: %AI and supporting tool spend / verified outcomes
Unit: USDUseful work delivered − human supervision and rework − tool costs. Time and money should be reported in their own units until a defensible valuation is established.
04 / Retrospective
Collect evidence, interventions and rework before claiming time savings.
Differentiate built, deployed, tested, approved and published.
Investigate root causes before adding another workflow.
Cross-check important personal, technical and public statements.
Prototype, build and iterate using the existing stack.
The human retains publishing and production decisions.
The question for next quarter
This dashboard is the evidence companion to a future first-person Substack story. Publication is pending editorial review.