It shows a working end-to-end agentic dev loop — task intake from QA/Jira/PR queues, isolated worktrees per agent, skills as pattern guardrails, sub-agents for traces and E2E tests — so engineering teams can copy the topology instead of inventing it.
The regulated-finance framing makes the human-as-final-verifier boundary explicit, which is the part most parallel-agent setups get wrong.
Ramana Siddanth Emani (Auditoria) describes running multiple coding agents in parallel across separate git worktrees, each guided by 'skills' to enforce patterns, to clear tasks pulled from QA reports, Jira tickets, and GitHub PRs.
Sub-agents pull traces and logs, write and run end-to-end tests, and report back, letting developers step out of the day-to-day loop while remaining the final verifier — applied at Auditoria to finance agents reconciling source data.
Transcript
The slowest part of shipping a production finance agent is not the model or the GPUs, it is you, the developer in the loop. Ramana Siddanth Emani's point is that the same agent harnesses you use to build products can automate your own developer loop. Coding agents can multiply how much you ship; run an army of them across separate git worktrees and they clear tasks in parallel, with skills making sure each one uses the right patterns.
The tasks come from where they already live, QA reports, Jira tickets, GitHub pull requests, and a sub agent pulls the traces and logs, writes and runs end to end tests, builds, and reports back, needing your context only at a few steps. Point this at your bug queue and a month later you have shipped far more, having stepped further out of the loop as the agents improve, while keeping a human as the final verifier. At Auditoria, where the work is finance, that means agents talking to agents and reconciling source data, so you spend your time verifying rather than grinding.
Speaker info:
- https://x.com/siddanth2486
- https://www.linkedin.com/in/siddanth-emani
Timestamps:
0:00 - Your bottleneck is you
1:05 - From bugs to pilots to production
2:37 - Automating the developer loop
3:03 - Coding agents that multiply output
3:39 - Skills for the right patterns
4:22 - Sub agents and where tasks come from
5:18 - Pulling traces, testing, reporting back
7:56 - Auditoria in the finance sector
9:04 - Stepping out of the loop safely
11:35 - Turning customer patterns into features
13:04 - Keep a human as verifier
