Sagar (@code_sagar) header
Sagar (@code_sagar) profile picture

AI Consultant • Forward Deployed • Travelling • Happy 🌞

LHR / BLR
Joined November 2020
Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)Photo by Sagar (@code_sagar)
Please support Alt News. pages.razorpay.com/altnews For some reason, If you cannot donate, a repost reaches someone who can. 🙏🏼
Fact-checking does not pause between elections, and the sanctity of our electoral process has become a central focus for us lately. We do that work the only way we can: reader funding. We are raising ₹12 lakh this month. Please support Alt News. pages.razorpay.com/altnews
13
97
271
30,465
Open to Work 🚀 I’ve recently been laid off from my current role and am now looking for a new opportunity.I’m currently exploring opportunities in Frontend Development, Full-Stack Development, and Software Engineering.If you know of any relevant openings or could help anyway🙏 – at Garhi Harsaru, India
8
2
1
16
1,373
+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window with just the right information for the next step. Science because doing this right involves task descriptions and explanations, few shot examples, RAG, related (possibly multimodal) data, tools, state and history, compacting... Too little or of the wrong form and the LLM doesn't have the right context for optimal performance. Too much or too irrelevant and the LLM costs might go up and performance might come down. Doing this well is highly non-trivial. And art because of the guiding intuition around LLM psychology of people spirits. On top of context engineering itself, an LLM app has to: - break up problems just right into control flows - pack the context windows just right - dispatch calls to LLMs of the right kind and capability - handle generation-verification UIUX flows - a lot more - guardrails, security, evals, parallelism, prefetching, ... So context engineering is just one small piece of an emerging thick layer of non-trivial software that coordinates individual LLM calls (and a lot more) into full LLM apps. The term "ChatGPT wrapper" is tired and really, really wrong.
I really like the term “context engineering” over prompt engineering. It describes the core skill better: the art of providing all the context for the task to be plausibly solvable by the LLM.
530
2,051
615
14,333
2,403,206
Resignation की ख़ुशी 🥹
807
442
302
5,770
1,401,749
🏴󠁧󠁢󠁥󠁮󠁧󠁿 Inglaterra: 4-2-3-1 en rombo, Kane de falso 9, Bellingham llegando desde segunda línea, Pontas invertidos, Presión alta, Rotaciones en el mediocampo 🇦🇷 Argentina: El que no se la pase a Messi es gay
228
8,521
220
117,007
3,182,215
He didn't win the cup. He won our respect. 🇳🇴
1,235
33,094
723
298,847
3,039,337
Replying to @sentra_app
@sentra_app can now provide memory directly to your AI agents! Sentra's new MCP integration lets your AI agents pull context from past conversations and your company's artifacts, including Jira tickets, Slack messages, emails, meeting transcripts, and more. Save up to 90% in token spend and double your query speed. No more racking up thousands in token costs or repasting context for the hundredth time. Works with Claude, ChatGPT, Cursor, and many more. One CLI install, integrate it in under two minutes today.
9
4
24
4,738
Agentic AI is reshaping the entire marketing workflow. Campaigns are moving 10–15x faster, personalization is getting sharper, and revenue lift can reach 10–30%. The companies getting ahead are redesigning how marketing gets done end to end. mck.co/42CSSiL
42
84
21
375
45,299
The ultimate goal of starting a company isn't to be rich, it's to bow to no one.
57
69
4
589
13,886
Sagar retweeted
You as a single person have more power today than a 20 person company of the past. That's insane. The internet gave you the ability to learn anything. Social media gave you the leverage to reach anyone. AI is giving you the ability to create almost anything. Please don't waste it
581
1,270
132
10,499
329,359
Today we're introducing TRIBE v2 (Trimodal Brain Encoder), a foundation model trained to predict how the human brain responds to almost any sight or sound. Building on our Algonauts 2025 award-winning architecture, TRIBE v2 draws on 500+ hours of fMRI recordings from 700+ people to create a digital twin of neural activity and enable zero-shot predictions for new subjects, languages, and tasks. Try the demo and learn more here: go.meta.me/tribe2
719
2,442
1,483
15,897
6,982,593
My new pencil art on paper. Shadows of the evening II
654
11,960
402
59,048
4,784,424
Sagar retweeted
Replying to @iam_smx
*trillioniare
12,511
18,155
4,976
215,374
17,699,542
Apparently, Pakistan will not finally decide on whether to take their T20 WC place until 2nd February. This is very sneaky and unfair on our squad, who need certainty and extensive preparation in order to perform at their best. Our captain is a professional baker.
603
1,687
159
24,713
761,601
Sagar retweeted
Microservices is the software industry’s most successful confidence scam. It convinces small teams that they are “thinking big” while systematically destroying their ability to move at all. It flatters ambition by weaponizing insecurity: if you’re not running a constellation of services, are you even a real company? Never mind that this architecture was invented to cope with organizational dysfunction at planetary scale. Now it’s being prescribed to teams that still share a Slack channel and a lunch table. Small teams run on shared context. That is their superpower. Everyone can reason end-to-end. Everyone can change anything. Microservices vaporize that advantage on contact. They replace shared understanding with distributed ignorance. No one owns the whole anymore. Everyone owns a shard. The system becomes something that merely happens to the team, rather than something the team actively understands. This isn’t sophistication. It’s abdication. Then comes the operational farce. Each service demands its own pipeline, secrets, alerts, metrics, dashboards, permissions, backups, and rituals of appeasement. You don’t “deploy” anymore—you synchronize a fleet. One bug now requires a multi-service autopsy. A feature release becomes a coordination exercise across artificial borders you invented for no reason. You didn’t simplify your system. You shattered it and called the debris “architecture.” Microservices also lock incompetence in amber. You are forced to define APIs before you understand your own business. Guesses become contracts. Bad ideas become permanent dependencies. Every early mistake metastasizes through the network. In a monolith, wrong thinking is corrected with a refactor. In microservices, wrong thinking becomes infrastructure. You don’t just regret it—you host it, version it, and monitor it. The claim that monoliths don’t scale is one of the dumbest lies in modern engineering folklore. What doesn’t scale is chaos. What doesn’t scale is process cosplay. What doesn’t scale is pretending you’re Netflix while shipping a glorified CRUD app. Monoliths scale just fine when teams have discipline, tests, and restraint. But restraint isn’t fashionable, and boring doesn’t make conference talks. Microservices for small teams is not a technical mistake—it is a philosophical failure. It announces, loudly, that the team does not trust itself to understand its own system. It replaces accountability with protocol and momentum with middleware. You don’t get “future proofing.” You get permanent drag. And by the time you finally earn the scale that might justify this circus, your speed, your clarity, and your product instincts will already be gone.
180
1,191
345
8,134
998,124
Sagar retweeted
Too many are interested in “tech” (by which they mean money) but they aren’t interested in tech (by which I mean math).
317
726
101
7,660
337,776
What makes a manager want to lean in, invest, and sponsor someone? As I’ve grown in my career and started managing teams, I’ve often been asked, by early-career colleagues & students, what makes someone stand out professionally? For me, there’s one consistent trait: Extreme ownership. It shows up in very simple ways: - You never need to be chased for an update - You proactively close loops - When you don’t know the answer, you take responsibility for finding it...by asking questions, pulling in the right people, escalating thoughtfully, and ensuring things are moving forward It sounds simple, but it is surprising how rare this actually is. And as careers progress, the form of ownership evolves - into prioritization, judgment, thoughtful delegation, and the ability to manage up, down, and across. This is what I continue to work on everyday too! But the core muscle is built early: the mindset that “this is mine to drive.” In every organization and region that I’ve been part of, this is the trait that quietly but consistently differentiates people.
3
6
22
1,515
The day is near when your company will start making AI products. If you want to be the face of the change. Read on:
2
7
1
30
5,795
ai is ozempic for corporations.
180
752
86
7,026
540,147