Salman Bareesh

Marketing engineer. I connect marketing problems to working technical systems.

[Salman Bareesh @Salman_Bareesh]

The best GTM system is still a narrow loop from signal to message to reply. Everything else is infrastructure looking for a job. https://t.co/b3hsAb0lt3

[Cody Schneider @codyschneider]

GTM engineering explained

Low IQ:

Get a list of the right people with real emails. Send them a good message. Put who replied in one place.

Midwit:

A Clay table with 47 columns and waterfall enrichment across nine providers, running on 50,000 rows
Building the data platform first — warehouse, reverse ETL, warehouse-native CDP — before a single campaign has been sent
A 60-node n8n graph nobody else can debug, which fails silently on a schema change
LLM calls doing work a regex does: "is this a real business," "extract the company name," "classify B2B vs B2C"
A 30-signal weighted ICP score, weights assigned by feel, reported to two decimal places
Nine overlapping data vendors: Clay, Apollo, ZoomInfo, Ocean, Keyplay, Common Room, Warmly, RB2B, plus two intent providers
"Signal-based outbound" monitoring 22 triggers — job postings, funding, new hires, tech installs, website visits — most of which fire constantly for everyone
A Slack channel per signal, all of them muted by week three
Perfect-data-hygiene project: dedupe, normalization, account hierarchy resolution, before there's revenue to protect
Waterfall enrichment across six vendors to move email coverage from 71% to 76%
Internal tooling built where a CRM field would do
Measuring records enriched, workflows shipped, "hours automated"
A full rebuild when a vendor changes an endpoint

High IQ:

The smallest pipeline that gets a correct message to a correct person. Two enrichment sources. One signal you've actually verified correlates with buying. Campaign live in week one, instrumentation added after it works. Anything that hasn't produced a meeting in 60 days gets deleted, including things you built.

[Salman Bareesh @Salman_Bareesh]

The useful primitive here is not another autonomous agent. It is a permissioned decision queue that knows which actions are safe to run and which ones deserve a human. https://t.co/DvT6EDbQpC

[GREG ISENBERG @gregisenberg]

10 Jev native products I’d build, ranked by how much fast, cheap decisions change the product:

1. Agent spend firewall

Before every purchase, Jev returns approve/review/deny plus a confidence score based on price, vendor, user rules and purchase history.

2. Self-healing tool calls

After an API error, Jev chooses retry, wait, change parameters, switch providers or escalate.

So now you have agents that recover from failure in milliseconds instead of restarting the entire workflow.

3. Irreversible action detector

Jev scores every step by reversibility before the agent sends an email, deletes a file, moves money or changes permissions.

You get aggressive automation for safe actions and human approval for consequential ones.

4. Dynamic permission engine

Instead of giving an agent permanent access, Jev decides which tool, data and spending limit it receives for each task.

So now all of a sudden, you get temporary, task-level permissions for enterprise agents.

5. Agent branch pruning

An agent generates 20 possible next steps. Jev scores them in parallel and kills weak branches before expensive reasoning begins.

Deeper agent planning at a fraction of the cost!

6. Production incident controller

Jev reads logs, deploy history, affected customers and service health, then chooses ignore, rollback, restart, page or investigate.

Someone like pager duty should build this because it's automated incident response that reacts before an engineer opens Slack.

7. Live negotiation policy

During a sales, procurement or collections conversation, Jev decides whether to discount, counter, hold firm, offer terms or escalate.

Reminds me of Clulely.

8. Autonomous refund desk

Jev evaluates order history, customer value, fraud signals, item cost and policy, then returns approve, reject or review.

Finally, instant refunds for good customers and focused review for risky cases.

Note: I'll be adding more Jev related ideas to https://t.co/QxoITW16zr and our agency https://t.co/YQJFV1Xlkt builds the biggest agentic products

9. Realtime marketplace dispatch

For every request, Jev chooses the provider using location, price, quality, availability, cancellation risk and customer preferences.

Big problem is that marketplaces need to rematch supply continuously as conditions change.

10. Confidence based human queues

Jev scores every agent decision and sends only uncertain, expensive or irreversible cases to a person.

One person can now supervise thousands of autonomous workflows.

LLMs generate possibilities. Jev chooses what happens next. The next generation of software will need both.

[Salman Bareesh @Salman_Bareesh]

Parallel sessions are the easy part. The real upgrade is handing an agent a task that can survive your laptop closing, your context switching, and your attention span. https://t.co/fBfaTavEdS

[ClaudeDevs @ClaudeDevs]

We've just added local support to Projects in Claude Code, so threads can now run on your own machine.

[Salman Bareesh @Salman_Bareesh]

outreach should follow the same boundary.

never imply access to a private contract.

use the timing pattern as a reason to research, not as permission to manufacture certainty.

[Salman Bareesh @Salman_Bareesh]

strongest case: a public procurement record with explicit start and end dates.

that can support an exact statement because the contract terms are actually public.

[Salman Bareesh @Salman_Bareesh]

the honest output:

estimated review window
confidence level
evidence used
assumptions

not a fake exact renewal date.

[Salman Bareesh @Salman_Bareesh]

most “contract renewal” signals are not private contract dates.

they are estimates built from public evidence.

that is useful only when the evidence quality remains visible.

[Salman Bareesh @Salman_Bareesh]

@codyschneider +
claude artifact
chatgpt - gpts

[Salman Bareesh @Salman_Bareesh]

@everestchris6 I want to make content like you!

[Salman Bareesh @Salman_Bareesh]

@leodev Wtf

[Salman Bareesh @Salman_Bareesh]

@robj3d3 Waiting for it

[Salman Bareesh @Salman_Bareesh]

I written good article on content automation but it doesn't have good impressions. Putting lot of efforts but I gain nothing. Sometimes I feel like I need to quit creating content on X.

[Salman Bareesh @Salman_Bareesh]

https://t.co/Zs7cuQdjcr

[Salman Bareesh @Salman_Bareesh]

we added more researchers.

more writers.

more critics.

more ranking logic.

then discovered the missing system component was still:

client-approved examples: 0

[Salman Bareesh @Salman_Bareesh]

@rakesh_rry will it supports CMS?

[Salman Bareesh @Salman_Bareesh]

Been using it for 1 month, yielding me good results in my research.

[How To Prompt @HowToPrompt__]

finally!

there is a free tool that gives your coding agents access to X, LinkedIn, Facebook, Instagram and more.

100% open source. 75k stars already.

[How To Prompt @HowToPrompt__]

finally!

there is a free tool that gives your coding agents access to X, LinkedIn, Facebook, Instagram and more.

100% open source. 75k stars already.

[Salman Bareesh @Salman_Bareesh]

@mattceras Same here, build lot of prospect list only using code