AI Ping-Pong with Polly (and Omnigent)

Sometimes the most entertaining way to test a new orchestration tool isn't to run a standard benchmark, but to lock two state-of-the-art AI models in a virtual room and make them debate historical facts. This week, I got to do exactly that using an interesting new tool called polly within the omniagent ecosystem.

The idea was simple: set up a relay where Claude and Gemini (specifically the Antigravity agent) pass a task back and forth, validating and revalidating each other's work.

However, getting there wasn't entirely smooth sailing. I see recent polly changes that seem to be working on Antigravity support but I presume that it is just heavily in beta and under active development - Simply because I couldn't get it to work cleanly on my local test setup out of the box. In a somewhat ironic twist of AI-assisted development, I ended up having Claude help me debug my environment and write the custom harness around Antigravity to get the toolchain working.

Once the harness was solid, the fun began. I decided to test their interaction on a simple prompt asking for a list of India's Prime Ministers (based on their first stint). I then pass that list back-n-forth between the two AI engines for cross-validation and updation. To avoid an endless loop, I limited the number of iterations to exactly two.

Here is the exact prompt and how it kicked off:

 ❯ ask antigravity to generate the list of prime ministers of india in the
 chronological order (of their first stint) and then pass the list to
 claude for validation and an updated list of the same. and pass that onto
 to antigravity for revalidation with the same request. Do this round trip
 only 2 times and display the resultant list.

   · thinking…
◆ I'll run this as a relay: antigravity generates → 
    Claude validates/updates → antigravity revalidates, repeated for 
    2 round trips. Starting with antigravity's initial list.

◆ Antigravity produced the initial list (15 entries). Round trip 1 —
   passing to Claude for validation + an updated list:

◆ Claude is validating now. Waiting for its result.

.
.
.

Watching the two models interact was fascinating. Antigravity would confidently output the initial sequence, Claude would meticulously review it (often catching nuance around interim Prime Ministers like Gulzarilal Nanda), and then Antigravity would process Claude's corrections. It functioned like a highly pedantic game of ping-pong.

While this specific test was just good fun, the real motivation behind integrating polly is much more practical. I've been working on a complex PostgreSQL B-tree index compaction patch to solve the index bloat problem that VACUUM leaves behind. Developing database internals is notoriously tricky, and I've been relying on Claude (and now Antigravity) to help write and re-write and review the code heavily.

Having two AI agents look at the developing patch from different angles has been invaluable. They continually find subtle bugs, naming inconsistencies, edge-case production gotchas, and deviations from C best practices. Instead of manually passing code snippets back and forth between different chat windows, the idea here is to see if polly (or a similar tool) can allow me to seamlessly automate this cross-validation part without my intervention.

Now that the Antigravity harness is patched up and working, I've proven that this dual-engine review process can work, and be an automated part of my Postgres hacking workflow. That said, because Google's API billing operates separately from the standard Google AI Pro account, this specific Claude-and-Gemini pairing was mostly a test run. For the near future, I may just end up cross-validating between Claude and Codex (or a similar alternative) to keep the pipeline running smoothly and cost-effectively.

For the curious, here is the Relay trace of that conversation, and the final result.

   Relay summary

    Hop               Agent                 Result
    ─────────────────────────────────────────────────────
    Generate          antigravity (Gemini)  15-entry list
    RT1 → validate    Claude                two changes
    RT1 → revalidate  antigravity           no changes
    RT2 → validate    Claude                no changes
    RT2 → revalidate  antigravity           no changes


   Resultant list — Prime Ministers of India (chronological by start of first term)


     1 Jawaharlal Nehru — 1947
     2 Gulzarilal Nanda (Acting) — 1964
     3 Lal Bahadur Shastri — 1964
     4 Indira Gandhi — 1966
     5 Morarji Desai — 1977
     6 Charan Singh — 1979
     7 Rajiv Gandhi — 1984
     8 Vishwanath Pratap Singh — 1989
     9 Chandra Shekhar — 1990
    10 P. V. Narasimha Rao — 1991
    11 Atal Bihari Vajpayee — 1996
    12 H. D. Deve Gowda — 1996
    13 Inder Kumar Gujral — 1997
    14 Manmohan Singh — 2004
    15 Narendra Modi — 2014

   One note worth flagging (the cross-checks agreed, but for completeness): this
   list counts Gulzarilal Nanda once at his first acting stint (1964). He also
   served a second acting term in 1966 after Shastri's death — both models
   consistently treated 'first stint' as the ordering key, so he
   appears a single time at 1964, which matches your request.
 

Keep having fun !!