Customer Relationship Agents by Clarify

The M in CRM shouldn't be you

Sales

Artificial Intelligence

CRM

Visit WebsiteSee on Product HuntTwitter ⧉

The best CRM I've used as a sales rep who's been in the game for for over 11 years...

It's so easy to get context on what happened in my meetings to connecting it to my instance of Claude Code to spin up SOWs and agreements and contracts to spinning up agents to manage my pipeline.

It is an incredible CRM made in the AI era.

Congrats to Patrick and the team

We've been looking for something like this at Yoodli for ages. So excited to finally see actual CRM agents be a reality!

Congrats on the launch!!! Do you guys make your agents primarily for support or sales?

Congrats on this launch - seems like such a no-brainer to take the M out of CRM and ask AI to do the job!

What was the hardest part of building the agents?

This resonates very well. In most CRMs I’ve used , the system quickly turns into another thing I have to maintain instead of something that actually helps carry the relationship. Would you say that the agents here are most useful in updating CRM records after calls or emails, suggesting next steps, or give you the context before speaking to someone?

The CRM maintenance tax is something I hear about constantly from smaller B2B operations, where the person closest to the deal is also the one manually updating fields at 10pm on Friday. The idea of agents that run on a schedule or a signal rather than waiting for someone to remember to log something feels like the right direction.

I'm curious how the agents handle situations where the underlying data is patchy or incomplete. Like if a contact hasn't had any activity in 60 days and there's no clear next step on record, does the agent surface that gap and flag it, or does it mostly work with what's already there?

This feels very useful. CRM admin is one of those things that takes way more energy than it should.
What’s the first agent most teams usually set up?

Love this! Having been using it ever since I heard about it. By far the best CRM in the market today. It's not the biggest. But its by far the smartest and the one that is not bloated with a bunch of graphs just because. It shows you the essential information and works flawless!

A bit biased because I watched the team build this, but can't emphasize enough how cool these agents are. I used to cry myself to sleep trying to build automations in zapier or workflow builders, and now I can wire those up with a sentence and a couple of minutes. Nice that I don't have to go outside of the crm to do it, too.

The 'relationship agents' framing is interesting — the hard part with any AI layer on a CRM is trusting the underlying data, since reps under-log and records go stale fast. Does the agent actively enrich/verify (pulling from email, calendar, web) to fill the gaps, or does it reason over whatever's already in the CRM? The first is far more useful but also where accuracy gets tricky.

The "set them fully autonomous or require approval before acting" toggle is the part that stands out to me — that's usually where automation tools force an all-or-nothing choice. Is the approval gate configurable per action type (e.g. let enrichment run free but always hold writes that overwrite existing CRM fields), or is it set at the agent level?

Cool product! would like to know the guardrails for agents not completing tasks, or we can control their usage.

The idea of a CRM that updates itself is appealing because manual data entry is everyone's least favorite part of sales. I'm curious, what's the biggest habit founders stop doing once they switch to Clarify?

The autonomous part is exciting, but the failure mode I'd worry about in a CRM specifically is a confidently-wrong write — merging the wrong duplicate, enriching a lead from a stale source, updating a field based on a misread signal. A bad autonomous write is worse than no write because it silently pollutes the source of truth and everyone downstream trusts it. Question for you Patrick: does Clarify ever say "I'm not sure" and hold instead of acting, or does every triggered agent always write something?

I like the idea that the CRM work finally moves into the background.

A lot of the painful part is not managing relationships, but keeping the system clean enough so those relationships don’t get lost. Pipeline digests, lead enrichment, and data hygiene feel like exactly the right things for agents to handle.

Personally, I’d probably start with follow-ups and pipeline summaries first. Curious what teams automate most often after setup: cleanup, enrichment, follow-ups, or reporting?

The interesting bit is not that the CRM can update fields. It is the authority model around each update: which signal triggered it, what data it touched, whether approval was required, and what receipt proves it happened.

How are you exposing that when an agent runs fully autonomously?