Agently - Your whole stack, running itself!
by•
Every other tool answers, retrieves, or runs brittle rules. Agently holds your whole company in context and does the work. 100+ connectors flow into one brain that never forgets. It links a Stripe event to a Slack thread to a Linear ticket on its own. When something needs doing, Jarvis routes it to an agent that runs it end to end: triggered, running, shipped. The work lands without you, nothing falls through the cracks. Connecting takes minutes. The layer between today's AI and tomorrow's AGI.
Replies
The "running itself" promise is the dream and the fear at once. As a solo builder leaning hard on agents, my honest worry is trust: how much can I actually hand off unattended before I need to babysit again? Curious where you draw that line.
Agently
@virko_kask Honestly the most important question in this space, and I'd be skeptical of anyone who answers it with "just trust it."
Our line is the point of consequence. The agent runs on its own for the most part: drafting, research, pulling context, prepping the deliverable. But anything that ships or touches the outside world (sends an email, posts, spends money) hits an approval queue and waits for you.
Two things keep that from being annoying instead of empowering: it remembers what you reject, so it stops proposing the stuff you don't want, and you can widen that line per action type as trust builds. You start at "propose everything" and move toward "send the routine follow-ups on your own."
So you're never babysitting, you're reviewing. And you review less over time. Trust should be earned, so we built it to be earn-able.
Agently
@virko_kask Ahmad here, I own the agent loop. The thing that lets us make that promise honestly: the guardrail lives in the runtime, not the prompt. Every tool call passes through a policy gate before it executes, first-deny-wins. Anything classified as consequential gets intercepted before it runs and dropped into an approval queue. When you approve, we replay the exact call, so what executes is byte-for-byte what you signed off on, no re-interpretation in between. There's a kill switch and per-run budgets so a bad run can't spiral. We're not asking the model to please behave, we're structurally stopping it from shipping without you.
Pazi
Looks super useful
Agently
@zvonimir_sabljic1 appreciate it legend!
Agently
@doganakbulut Agently runs on Claude (Anthropic's Opus 4.8), and we match the right model to each job under the hood — so you don't have to pick or wire anything up.
Curious though: is model choice something you'd want to control, or more a "just make it work" thing for you? 🙌
Agently
@doganakbulut @ahmadhajj Yup what Ahmad said is correct, we do run multiple models throughout the process but the model you interact with Jarvis is Opus. If you would like to BYOK or run it with your own model, do let us know
The Stripe event to Slack thread to Linear ticket auto-linking is the interesting claim - most tools make you wire those correlations by hand. On day one, before it has any history, how does Agently decide two events across different systems belong to the same thread of work: is that learned from your data over time, or seeded from rules and shared entity IDs so it is useful immediately? And is the never-forgets memory scoped per connector, so revoking one integration also purges what it learned from that source?
Agently
@noctis06 The minute you connect the brain, it back fills data, tracking how your company has been behaving even before you ever decided to use the solution.
As for actual clean slate activation, this is probably the cleanest way to use Agently anyway. On onbaording, it asks you what your idea is, if you have a website, etc... Spins up 5 tasks to figure out your ICP, your competitors, drafts leads and gives you outreach, then the game begins.
Revoking an integrations never removes the context, it just cuts the streaming of data, context is still there.
Got it, so revoke stops the stream but the learned context stays. That's the part I'd want crystal clear before connecting a sensitive source: is there any explicit purge that actually removes what the brain inferred from a connector, say a customer invokes deletion or I offboard a tool, or is that context effectively permanent once ingested?
HarnessRouter
Congrats on the launch, Ahmad and Omar! The temporal-graph approach to memory is the right call. most "AI chief of staff" tools quietly break the moment two systems disagree. How do you handle the case where two integrations report conflicting facts at the exact same timestamp, does provenance alone decide, or is there a manual tie-breaker?
Agently
@renchu_songThank you 🙏 and you've found the exact edge most tools fake their way through. Our answer: a true tie is precisely when we refuse to auto-decide. Provenance is a signal, not a verdict, so when two sources genuinely collide at the same moment and neither is clearly authoritative, we don't silently pick a winner, we hold both as competing facts, flag the conflict and wait for more information to decide the winner.
It is worth noting that your interactions on the app get also logged into the brain, if the conflict comes up in a prompt and you happen to choose the right path for this specific issue, it also gets resolved in real time
Curious to know how it will manage all of our marketing KPIs and initiatives.
We are looking to build an AI VP of marketing for our team which sits in our team discussions
Agently
@sohraab_joshi1 love this, an AI VP of Marketing is exactly the shape Agently is built for. The way it comes together: your marketing context lives in the brain, goals, campaigns, analytics, what's worked and what hasn't, so the agent reasons from your actual numbers, not vibes. It tracks your KPIs across every conversation, tool and app against your own targets, flags what's slipping, proposes the next initiative, and drafts the work, then waits for your sign-off before anything ships. And because it lives where your team already talks, it's a participant, not one more dashboard to go check.
You can book a call with me and well get you set up
@omarships Yes let's chat, where can I find a book meeting link?
Agently
@sohraab_joshi1 on our website, booking button in the hero section
Congrats on the launch — linking a Stripe event to a Slack thread to a Linear ticket on its own is the part most agent products hand-wave.
The question I keep landing on with end-to-end autonomy: an agent triggered at T1 and shipping at T2 — what does it re-read in between? If someone closes that Linear ticket, or the payment gets refunded mid-run, does the approved action still fire against the state it was approved against?
That one doesn't look like a bug when it happens — nothing errors, the agent just acted on a version of the world that had moved. Curious whether your approval step re-evaluates at execution time, or binds at approval time.
Congrats on the launch. The shared company context across 100+ connectors is ambitious, but the part I’m most interested in is the approval boundary. Can admins scope an approval to an exact action, resource, amount, and time window? And when a cross-tool workflow partially succeeds, does the receipt show retries and whether the action is safe to replay?