Meet Lina. Lina is the assistant in LinkedMash. She searches your saved posts, drafts in your voice, tells you what to do next. Today I gave her a face. I wanted a personal connection with the AI I’m building, not another generic avatar. This is her. Day 58/100. LinkedMash → $2k MRR. Now - $349.15 (+$0).

LinkedMash made $748 in August 2026, after fees. Day 53 of 100, taking @linkedmash to $2k MRR. Current: $339.15 (+$10 MRR). This month: $748.87 collected, net MRR $249.50 to $339.15, up 36% 36 active subs $9.42 ARPU 913 visitors 1.64% of them paid July collected $722.15. Annuals make every month look like a spike or a desert. Public $300 by 31 July. Crossed it on 18 August. August was supposed to be for selling. The month still went into build work. The number moved $89.65. Building is the part I am good at, so it is the part I kept choosing.

Set up my first @bot. Named it @linkedmash Growth. Day 49 of 100, taking LinkedMash to $2k MRR. Current: $312.15 (+$0 MRR). - Gave it one goal: take LinkedMash from $300 to $2k MRR - It figured out what steps to do - Connected DataFast and Stripe - Did not connect GitHub at first. Grok has its own computer - It asked for the GitHub URL, but I am on Super Grok only, so it asked me to upgrade - Later asked it to figure out how to raise a PR - It asked for access to my computer, then found a way to open the PR Tried OpenClaw and Hermes earlier. Grok setup felt easy. It handled most of the technical complexity. Setup took about 2 minutes. If you want to try Grok Bot, open a new bot, give it a goal, and ask what to do next. It will guide you. Meanwhile I need to explore more in this new world. Interesting days ahead.

My search fix looks dead for three weeks in Bing. Then it isn't. Day 48 of 100, taking LinkedMash to $2k MRR. Current: $312.15 (+$0 MRR). On Day 13: LinkedMash was missing from page 1 of Bing for its own brand name. Fixed 11 meta descriptions to 160 characters, submitted 13 URLs through IndexNow, requested a recrawl. The chart proves visibility returned. It does not prove why. Do not judge search work the day it ships. The feedback can arrive weeks later.

Day 24 of 100, taking LinkedMash to $2k MRR. Current: $249.50 (+$0 MRR). Shipped Discover feature in LinkedMash.

8 out of 10 agent frameworks launched this year will be dead by Q4. The 2 that survive aren't the ones trending today. Rohit's piece is the cleanest filter for what to actually pay attention to in 2026. Worth bookmarking. 5 tests to run any new launch through: 1. Will this matter in 2 years? Wrappers around frontier models have a 6-month half-life. Primitives like protocols, memory patterns, sandboxing last years. 2. Has someone you respect shipped real production work and written a postmortem? Marketing posts don't count. "We tried X and here's what broke" is worth 10 launch announcements. 3. Does adopting it force you to throw out your tracing, retries, auth, config? 90% of frameworks trying to be platforms die. Good primitives slot in. 4. What's the cost of skipping for 6 months? For most launches: zero. The winning version will be clearer. Skipping isn't falling behind. 5. Can you measure if it actually helps your agents? No evals means guessing. Teams without evals ship on vibes and ship regressions. 5 primitives that compound: 1. Context engineering. Context is state. Every irrelevant token costs reasoning quality. By step 8 of a 10-step task, the original goal is buried under tool output. 2. Tool design. 5 to 10 well-named tools beat 20 mediocre ones. One team cut retry loops 40% by rewriting error messages alone. 3. Orchestrator-subagent pattern. Default to single-agent. Reach for multi-agent only when you hit a real wall. 4. Evals plus golden datasets. Highest-leverage habit. Most under-invested. 50 hand-labeled examples in an afternoon is enough to start. 5. File-system-as-state with think-act-observe. Claude Code, Cursor, Devin, Aider all converged here. Model is stateless. Harness is stateful. The catch: The actual professional skill is being uncool about what you don't pick up. The trending framework this week will have cheerleaders for 14 days. 6 months later half are unmaintained. Skip in 2026: AutoGen for production, CrewAI for production, autonomous agent pitches, naive parallel multi-agents, per-seat pricing for new agent products. If your agent only works with one model, that's a smell, not a moat.

I barely visited Twitter today, but I was able to catch up with what happened yesterday!

Shipped a big update to Twitter Lists digest 🎉 Now, you can get a summarized version of tweets from your favorite accounts - all in one email! Who wants to try? Drop 👋 in the reply

Bonus+ To Search your Twitter bookmarks, Use @TweetsMashApp to filter by Text, Media, Threads, Year, Author, Tags and more!

Recently got my hands dirty with the "Advanced Search" options in X. Sharing here, 10 most "Advanced Search" options to discover your favourite tweets on this platform.

Tweetsmash Pricing Revamp! 🎯 We looked hard at last month's 80% churn and discovered that users had different needs. Many just wanted to export Twitter bookmarks, while others sought deeper value. 🤔 1/5 🧵

April is our most brutal month ever! 🤯 It’s the first time our expenses exceed revenue and also an all-time low in terms of Income! For the next 30 days, either I am going to reach $2.5k in revenue or fail publicly. 🤞 Wish me luck! 1/9 🧵 #buildinpublic

Tweetsmash handpicks my Twitter bookmarks and turns 'em into "Viral Picks"🔥 Check out my all-time fave Top 5 Viral Pick tweets!✨ Thread👇🧵

Finally, we were able to break Twitter’s API limit by bringing back the extension! ✅ Export your Twitter Blue Bookmarks folders ✅ Export till your first bookmark ✅ Instantly sync bookmarks + folders to Tweetsmash & notion Adding more for a seamless sync experience!

8+ AI Tools to level up your marketing! Thread 🧵

Business plan to build a $15k/month side hustle, How to be happier & Consistency is everything! 🧵 My 5 favourite tweets of the week: