CesarAG

growth & marketing @aiscwork

[CesarAG @cesargomz29]

@clayul It was always about the data

[alex @alextalksai]

🚨 ESTO ES UNA LOCURA

Este tipo ha descubierto la verdadera razón detrás del shadowban y te enseña a quitártelo empleando su MCP.

también te enseña a hacerle seguimiento a tu desempeño en tik tok y en Instagram usando auto-pilot.

Te dejo los detalles aquí abajo 👇

[CesarAG @cesargomz29]

@vivistac Que interesante esto

[silvan @silvanrec]

tu en 5 años yendo a trabajar a las 6am porque pasaste de largo este post

[CesarAG @cesargomz29]

@alextalksai Una absoluta locura

[CesarAG @cesargomz29]

@silvanrec cuántas veces posteé sin saber si tiktok lo había marcado

[CesarAG @cesargomz29]

@kaido_xr $5k/mo retainers for ad research are completely finished.

[CesarAG @cesargomz29]

@mardehaym I'll keep it, it's something that will work for me in the future

[Mark Ajzenstadt @mardehaym]

A performance marketing platform with paying advertisers asked us to make their product operable by AI agents.

We delivered the foundation in six weeks, the MCP service twelve weeks later, and the client's CTO now ships production code through his own AI harness inside gates we built.

I want to walk through how, because "AI-enabled adtech" is on every deck in the category and almost none of it means an agent can operate the platform.

Their codebase had real advertisers, real offer configurations, and real money moving through conversion data.

This is brownfield, not a weekend prototype demo.

February and March, we didn't touch AI.

We built the foundation the agents would need: versioned management APIs, a dedicated API key type with its own authorization gating, an SDK surface, published Swagger docs.

Teams skip this constantly. They wire a model to the UI endpoints, the payloads are ten times too large for an agent's context, the first write corrupts a live offer, and the pilot dies. I've seen it across 100+ engagements.

When someone says "our platform isn't ready for agents," they almost always skipped the API surface.

June 9, the MCP service went live. Tenant-scoped, read-only by design. Offer listings, change logs, performance summaries, conversion data. An early user couldn't damage a live configuration because there was nothing to damage with.

July 1, the first write tools: pause, share, clone an offer, update a conversion status. July 9, the second wave: update offers, resume paused ones, create ad-hoc conversions for integrators.

The endpoints were purpose-built for language models. Narrow summary calls, current-date context injected for month-only queries, response-size caps, latency work. Large payloads break agent workflows, so the surface was designed around the agent rather than reused from the UI.

Their CTO ships production code himself, through his own AI agent harness. We own the API surface, the architecture, code review, QA and release. Same repository, same board, same branching strategy, same quality gates, with guardrails enforced at GitHub level.

April 14 was the first production delivery from that workflow: a query optimisation where the agent validated its own work by diffing old and new SQL against production data, row for row.

The release count came from three things: automated AI review on every pull request since January, tests scoped from the PR diff with the bulk of new test code generated, and a documentation set of around 70 system documents kept in the repository so it doubles as context for the agents.

Behind it, this engagement is one of the first two pilots for Velocity Core, our own agentic delivery system.

A ticket status change fires a webhook, an isolated agent plans, executes, runs CI and opens a PR for human review.

When CI fails, the failure and the developer's fix are recorded and served back to future runs. Alpha, tested on real tickets, with the client's CTO inside the loop.

Their CEO connected his own AI assistant to the platform. As far as we know, very few platforms in performance marketing can say that today.

That's what our Velocity Framework was built for.

[CesarAG @cesargomz29]

Imagine your TikTok account telling you exactly why a post stopped getting reach — then fixing the problem automatically.

That’s basically what Tokportal is building: real account signals + millions of posts + AI-powered workflows that keep improving over time.

[Vincent @tellenne_]

We just made a MAJOR upgrade in how you can track your TikTok and instagram performances & health on auto-pilot.

All directly included for every tokportal users:

- Your accounts health metrics (the real proven data behind "shadowban" superstition)
- Account flags, soft-locks, bans
- Feed distribution status of a post (e.g. if TikTok flagged your video)
- AI detection / AI flags
- Sound use distribution
- Full comments analysis
- ..+30 more

From now on, you can ask tokportal MCP to build any auto-improving workflows -> video got flagged -> correlation with your other posts -> re-add warming on the account -> repeat to millions of views.

We also trained AI with millions of posts data we have, let me know if you have questions!

[CesarAG @cesargomz29]

@naldzyul el refresh compulsivo a las 200 visitas es un ritual que todos conocemos

[CesarAG @cesargomz29]

@tellenne_ I find everything that can be done with this tool interesting

[Vincent @tellenne_]

We just made a MAJOR upgrade in how you can track your TikTok and instagram performances & health on auto-pilot.

All directly included for every tokportal users:

- Your accounts health metrics (the real proven data behind "shadowban" superstition)
- Account flags, soft-locks, bans
- Feed distribution status of a post (e.g. if TikTok flagged your video)
- AI detection / AI flags
- Sound use distribution
- Full comments analysis
- ..+30 more

From now on, you can ask tokportal MCP to build any auto-improving workflows -> video got flagged -> correlation with your other posts -> re-add warming on the account -> repeat to millions of views.

We also trained AI with millions of posts data we have, let me know if you have questions!

[brenz. @brenzhills]

yo en 2030 después de grabarme trabajando y poner a tres robots a hacer mi trabajo para siempre:

[CesarAG @cesargomz29]

@brenzhills the jensen truck scene alone deserves an oscar lol

[CesarAG @cesargomz29]

@mattknowsai Definitely a real madness

[CesarAG @cesargomz29]

Imagine having a creative research team that never sleeps.

That’s basically what Lightreel is building for Meta Ads.

Millions of ads → winning hooks → new creative ideas → more testing.

And you can try it for free.

[Lightreel AI @lightreelai]

Introducing GPT-6 for Meta Ads.

Just describe your product and Lightreel searches millions of Meta ads to find:

-> competitor formats
-> trending hooks
-> feedback on your ads

Start improving your ROAS with 100x creative volume. It's free to try!

[CesarAG @cesargomz29]

@heyfredds It undoubtedly makes the process easier

[CesarAG @cesargomz29]

@liambraus Exactly it's the future

[CesarAG @cesargomz29]

@liambraus the fact that you don't need to leave the claude chat is actually a bigger deal than it sounds. zero context switching

[CesarAG @cesargomz29]

@robinstetic Without a doubt, that's what makes the difference