Maker · Operator · Bay Area

I build the paved road for agentic work.

Power users find the tools. Organizations need a default: one path that is easier than the old way, governed enough for a payments company, and honest about what shipped. That operating model is what I make.

Mohit Dogra · Walnut Creek / Bay Area

See the work Try the paved road
10 yrs
Visa Direct delivery through GenAI and agentic toolchain programs
10→80%
daily active in CMS Product Development on the paved road
~3 mo → ~10 d
time to first working agent after the paved road landed
~2× / −60% / −30%
deploy freq / lead time / CFR on migration programs, not the toolchain

Selected work

Case studies with named scope

Four builds. Scope is named carefully. Engineering built skills, connectors, and the pipeline; I owned the program design, adoption path, and measurement. Scroll the rail.

Product delivery
Product delivery Visa Direct

A decade of Visa Direct delivery

Concept-to-market delivery on a large payments product: regulatory launches, multi-org plans, and sitting next to product without owning the PRD. Argentina, wires, early platform modernization, and Reimagine. Influence without a reporting line was the default.

  • One integrated plan when product, processing, and compliance did not share a backlog.
  • Cut to GA-critical versus follow-on against hard regulatory dates.
  • Later: PMO CoE cadence (QBR/QEP) across three orgs and 500-plus engineers, with delivery-health as telemetry rather than a monthly narrative.

Outcome: dates held under real constraints; cadence that other delivery managers could run after handoff.

Agentic AI
Agentic AI Program design

GenAI guild to a governed agentic toolchain

The guild proved AI worked for power users. It did not scale. I defined and led the program for one paved road: one-command setup, identity that non-engineers could use, MCP-scoped connectors, a human merge rule, evals before keys, and telemetry that classified shipped work rather than vanity usage.

  • Program design was the job (~80% of what I owned). Platform and engineering built skills, connectors, and the pipeline.
  • Evals before exposure: beat the incumbent on our test track or no keys. Rings and kill signals before broad rollout.
  • I did not write CODEOWNERS, own security controls, or build the platform. I owned the rules, the rollout path, and the honesty layer on usage.

Outcome: time to first working agent from about three months (guild era) to about ten days on the paved road; pattern used beyond the original org.

Adoption
Adoption CMS Product Development

CMS Product Development: 10% to 80% daily active

This number belongs to one denominator: CMS Product Development. Not company-wide. Six weeks on the paved road, and it held week over week. Mandate was not the lever. Making the default easier than the old path was.

  • One command to start, skills for work teams already did, a corp-ID path so product people were not locked out by developer-ID gates.
  • Champions and pods: exit was a merged PR, not a slide. Their engineer demoed to their EM.
  • Telemetry for stuck teams (missing connector, quiet champion, bad output) visible in days.

Outcome: 10% to 80% daily active in CMS Product Development; org-wide claim is the pattern and scale of use, not an 80% company DAU slide.

Migration
Platform delivery Migration

Platform and migration delivery (DORA on this program only)

Separate from the toolchain. Monolith-to-microservices and CI/CD with canary rollouts across production applications on a payments platform. Partnership with engineering on deploy automation, N and N+1 trains, and treating "no client change" as a testable contract after a canary taught that lesson the hard way.

  • Deployment frequency roughly doubled; lead time down about 60%; change-failure rate down about 30%.
  • Those DORA figures belong to migration / CI programs only. They are not pasted onto the agentic toolchain story.
  • On the toolchain, the quality tell was review latency and change-failure staying flat as volume rose.

Outcome: faster, safer release path on migration programs; clear wall between those numbers and AI adoption metrics.

Operating system

How I design the default

Light enough to survive handoff. Strict enough for a payments company. Click through the paved road, or use arrow keys when the toy is focused.

The paved road

Brand interaction: Power users → Evals → Rings → Kill signals → Measurement. Play it like a system diagram you can walk.

    01

    Evals before exposure

    No keys until the offering beats the incumbent on a real test track. Shiny tools fail that gate on purpose.

    02

    Rings and kill signals

    Cohorts before company-wide. Kill criteria written before rollout, not after the first bad week.

    03

    Measure shipped work

    Invocations that become artifacts, time to PR, started versus finished. Usage alone is vanity.

    04

    Cadence that survives handoff

    Standard artifacts, decision logs, coaching into the seat. If only I can run it, it is not done.

    Notes

    Short pieces from the work

    Not a blog farm. Four notes drawn from themes I actually ship against.

    Builds · Agentic paved road

    From power users to a governed default

    A guild proves the tech works for people who already know how to wrestle it. A paved road is different: one-command setup, identity non-engineers can use, connectors scoped on purpose, and a human merge rule. Program design owns the rules and the rollout path. Engineering owns skills, connectors, and the pipeline. Confusing those two jobs is how you get a platform nobody adopts.

    Theme from the GenAI guild → toolchain program

    Notes · Evals & rings

    Evals before exposure, kill signals before hope

    Keys are the scarce resource. Beat the incumbent on a real test track or no keys. Write kill criteria before the first cohort, not after the first bad week. Rings keep the blast radius honest. When volume rises, the quality tell is review latency and change-failure staying flat, not a spike in chat messages.

    Theme from rollout design behind the paved road

    POV · Kill signals

    Agentic kill signals are a design artifact

    If you cannot name what would make you stop the rollout, you are hoping. I write kill signals with the same seriousness as success metrics: review latency climbing, change-failure drifting up as volume rises, stuck teams invisible for more than a few days. Those lights belong in the program design, not in a postmortem.

    Voice from governing agentic rollouts

    POV · Measurement

    Measuring shipped agent work, not chat

    Invocations are cheap. Artifacts are not. I care about invocations that become a PR, a ticket closed, a decision logged. Time to first working agent. Started versus finished. If your dashboard celebrates message volume, you are optimizing for the wrong dopamine. Measure what left the building.

    Honesty layer on agent telemetry

    About

    Who is behind the work

    Mohit Dogra is a product delivery and program design operator based in Walnut Creek, Bay Area. A decade at Visa on Visa Direct delivery, then GenAI guild and agentic toolchain programs.

    He designs operating models that take agentic tooling from power users to a governed paved road: evals before exposure, rings and kill signals, and measurement on shipped work. The craft is TPM and product delivery. The identity is maker of systems that other people can run.

    Scope is named carefully. No inflated platform-build claims. Metrics stay with the program that earned them.