Pandidharan

Final-yr CS · building JobHunt AI · open to founding eng roles · writing since 8 Jun
Day 72 · public proof
Their logs30
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles17 Oct
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles11 Oct
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesBuilt · 9 Oct
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles30 Sept
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles14 Sept
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles4 Sept
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles3 Sept
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles1 Sept
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles31 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles30 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesLearned · 28 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles26 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles25 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles24 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesBuilt · 23 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles22 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles21 Aug
◈ Open to sharpen
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesStuck · 20 Aug
Picked at Proof · 14 Nov
◈ Open to sharpen
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesBuilt · 19 Aug
◈ Open to sharpen
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesStuck · 18 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles18 Aug
◈ Open to sharpen
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesBuilt · 17 Aug
◈ Open to sharpen
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesBuilt · 16 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles15 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesDecided · 14 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles14 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng rolesLearned · 11 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles7 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles6 Aug
PandidharanFinal-yr CS · building JobHunt AI · open to founding eng roles5 Aug

Paid for thinking · 1 why picked at Proof

Picked logs · 1
14 Nov
Picked · 14 Nov
Day 20: Started Phase 3 of the project. Built retrieval into the agent and executed first live voice test which failed. Greeting exchange worked ("Hi, am I audible?" → answered), but llm_ttft was already 7.4s because the call needed two retries against a "503 UNAVAILABLE" - model currently experiencing high demand , before succeeding. The very next turn - "Introduce yourself. In short." — which the grounding prompt correctly routes through `search_my_background`, since "introduce yourself" is a factual claim from the corpus — hit a "429 RESOURCE_EXHAUSTED": `generativelanguage.googleapis.com/generate_content_free_tier_requests` capped at "5 requests/minute" for `gemini-3.7-flash`, the model `GEMINI_MODEL=gemini-flash- latest` currently resolves to. The plugin retried three more times internally and then raised `APIConnectionError: failed to generate LLM completion after 4 attempts`. `agent_state` dropped from `thinking` back to `listening` with nothing spoken, which lead to a infinite hang, because nothing tells the visitor anything went wrong. So now I need to choose a different model which has atleast 10 RPM. Also implement a fallback message, so when same error occurs it can be identified instead of dead silence for 5 mins which I experienced a few mins ago.
5 months on Proof
■ weeks with logs■ quiet week
76 logs · 42 say why
How Pandidharan thinks
Decides and owns the call — moves before being told.
↳the log that shows it
articulate·curious·decisive
⤳ Sharpens others · 1
How Pandidharan thinks, mapped · lit by their own logs · 8 showing
How they reason · the four moves
Evidence
argue from what you saw, not what you assumed
Alternative
name the option you didn't take
Assumption
surface what you're taking on faith
Tradeoff
state the cost of the call
What their logs say
Curious
you ask, not just assert
Articulate
you write the full why
Ownership
you own the call & the miss
You update
change your mind on evidence
Showing — it’s in their logs; tap to see them allno %, no rank — evidence, not a score.
Milestones3 earned
Day 30 · Jul 12Day 20 · Jun 29Day 10 · Jun 17
About
PythonReactMachine learningLLMs / GenAIDockerFastapiMySQLMongoDBPostgresRedis
🎓 Saveetha Engineering College
Projects
ai-digital-twin-blue
ai-digital-twin-blue.vercel.app ↗
1 log
job-boards.greenhouse.io
job-boards.greenhouse.io ↗
1 log
news.ycombinator.com
news.ycombinator.com ↗
1 log
GitHub
GHgithub.com/Pandidharan22 ↗

Repos show when they’re linked from a log. Proof doesn’t count stars or commits.

Want a page like this?
Write what you tried, a few lines a day. People who’d hire you read it.
Start your Proof