Karthik (@kartikktwt) — sponsored posts & rates · unfair.so

Browse more creators

unfair.so/x/@kartikktwt

Karthik

Karthik1.7K

Karthik

This creator added themselves. Not verified by unfair.so.

I talk about my life, tech stuff that interests me (backend, Go, Kubernetes, agents), and occasionally some slop | DM for work/Collab

@kartikktwtAI AgentsOpen SourceDevtools

1.7KFollowers

467Median impr. / post

3.2%Engagement

4

Paid partnerships

In their audience

4 affiliated with @hackmamba follow Karthik

@iChuloo

@heygandharva

@alwayspriyesh

@khanasjad21

3 affiliated with @hydra_db

3 affiliated with @amazon

3 affiliated with @superteamin

3 affiliated with @cloudnativefdn

3 affiliated with @gmi_cloud

336 verified followers analyzed

@iChuloo

@heygandharva

@alwayspriyesh

@khanasjad21+33248 engineers42 AI engineers39 devtools engineers27 founders11 AI creators11 creators

18–24 core age group

39.1%

30.4% of audience in India

🇮🇳

Last 7 days200 posts analyzed · replies not counted · updates weekly

ImpressionsEngagements

46.2K23.1K0

1.1K5490

Nov 7Nov 8Nov 9Nov 10Nov 11Nov 12Nov 13

Past collabs

Karthik@kartikktwt · Nov 11you don't need 50k followers to get paid for trying new ai tools hackmamba's growth champions gives you early access to new models, coding agents and dev tools. you try them in your own projects, post what you actually think (good or bad), and get paid in usd through stripe. a small audience is fine if it's the right one, you can join from anywhere in any language, and you see the fee and deliverables before you accept anything. if you already post about the tools you use, you're doing this for free right now 👀 here's the link: https://hackmamba.io/growth-champions/ you set up a profile with your interests and the channels you post on, and they reach out when a program fits your audience

hackmambaPaid partnership435 views

Karthik@kartikktwt · Oct 22One detail i found interesting while reading this: a single research question can fan out into 30 search queries running concurrently. but that creates another problem. duplicate URLs across results, noisy sources, pages with no useful content, and claims that need to be grounded in actual sources. This guide from octen walks through building a researcher around that pipeline: - `broad_search` for concurrent query fan-out - source shortlisting to filter and deduplicate results - `extract` to pull page content as markdown, with metadata and query-specific highlights - a tool-calling loop that synthesizes the findings and maps citations back to pages it actually read The implementation uses TypeScript, the Anthropic API, and MCP. if you're building research agents, the interesting bits are in how these pieces fit together, not just the final LLM call. https://octen.ai/guides/how-to-build-a-web-researcher-with-mcp-web-search?channel=x-octen

octenPaid partnership819 views

Karthik@kartikktwt · Oct 21Banger read from octen topics covered: - Why agents stall when they rely on plain search links and snippets - Model-native research APIs (OpenAI, Gemini) versus web-research infra (Octen, Exa, Tavily and others) - How 8 deep research APIs compare on features, cost and limitations - Latency budgets and handling lots of searches at once for real-time agents - Full-page extraction and getting past anti-bot protection - Comparing cost per finished research task instead of cost per request https://octen.ai/versus/best-deep-research-api-for-ai-agents?channel=x-octen

octenPaid partnership255 views

Karthik@kartikktwt · Oct 20small tl;dr on deep research APIs coz everyone building agents should know this search api = gives u links + snippets. ur agent does the rest. deep research api = plans the research, searches in multiple rounds, reads full pages, cross-references sources, and gives u a cited report. 2 types: model-native = openai, gemini. the same provider handles planning + search + writing. web infra = octen, exa, tavily, firecrawl, parallel, perplexity. research capabilities u can plug into ur own agent stack, with varying levels of model flexibility. some jargon u should know: SERP snippet = the 2-line preview google shows u. useful for discovery, but rarely enough for an agent to reason deeply. fan-out = firing 20-50 searches in parallel to explore different angles of a question. field-level citations = every value in ur JSON output has its own source, not just a citation dumped at the end. plan review = the agent shows u its research plan before executing it, so u can inspect or modify the direction. if you are building/learning research-heavy agents, give this article a read, it covers the major deep research APIs and their key capabilities 🫡 https://octen.ai/versus/best-deep-research-api-for-ai-agents?channel=x-octen

octenPaid partnership506 views

Planning a launch?Karthik is one of 200 curated B2B creators. Tell us what you are launching and we will put the shortlist together.

[email protected]·@notmiramurati

1 picked$50

Karthik (@kartikktwt) — sponsored posts & rates · unfair.so