Parahelp retweeted
When your product ships daily, how do you keep an AI support agent up to date?
We just released @parahelp_ai automations for support operations tasks like this.
Here's how you build an automation that updates your agent whenever relevant parts of your GitHub codebase change.
Parahelp now integrates with @usepylon.
Parallel Web Systems, Juicebox, and Eve Legal already run their Parahelp agents in Pylon. Their agents resolve tickets across email, live chat, and Slack - from product questions to technical troubleshooting.
parahelp.com/blog/pylon-inte…
Parahelp retweeted
If a tool has an API, you can connect it to your AI support agent - just by chatting with Parahelp.
Watch me build a connection to Linear so our own support agent can check and file feature requests the same way we do internally.
.@Mintlify grew 10x in a year.
CEO @handotdev shared what's in their internal AI stack:
Code: @claudeai @cursor_ai @tryreplicas
Design: @replit @lovable
Personal agents: @gumloop
Code review: @cursor_ai @greptile
Agent ops: @slackhq @temporalio
Support triage: @parahelp_ai @plainsupport @linear
Sales intel: @tryattention @salesforce @meetgranola
Knowledge base: @notionhq @mintlify
Parahelp retweeted
Today, we’re launching Parahelp 3.
With Parahelp 3, we’re doubling down on building the best product for startups to scale delightful customer support - at a time when AI is accelerating how fast they move.
@parahelp_ai is now an AI support team that stays up to date on your product to deliver delightful support to your customers:
- A Customer Agent that resolves your most complex support tickets
- An Internal Agent that builds your Customer Agent and updates it at the moment your product changes¨
Thanks to everyone who has helped us get this far. We’re very excited about the next chapter!
Read more in the comments.
Parahelp retweeted
Excited to reintroduce Parahelp with a new website, use case library, and customers, including the teams at Cursor, Speak, and Fyxer.
parahelp.com/
Parahelp retweeted
Parahelp is one of the top vertical AI companies to come out of YC.
They are automating support for AI-native companies like Perplexity, Replit, & ElevenLabs.
Did a deep dive with the founders on how real agentic systems are built and their recent Series A with @jaltma.
Parahelp retweeted
Today, we’re releasing the Parahelp Assistant.
It’s an AI engineer that makes it ten times faster for our customers to ship updates to their Parahelp support agents!
@parahelp_ai
Parahelp retweeted
Congrats to the @parahelp_ai team on their launch and $21.2M in funding!
In the past year, Parahelp has become the go-to AI support agent for the world's fastest-moving software companies.
Today, we’re announcing Parahelp to the world and that we've raised $21.2M.
In the past year, @parahelp_ai has become the go-to AI support agent for the world’s fastest-moving software companies, and we're proud to say that 0% of the companies we've onboarded have churned.
We’re hiring exceptional engineers, so if you’re excited to build on the frontier of applied AI for customer support, please reach out!
Parahelp retweeted
Today, we’re announcing Parahelp to the world and that we've raised $21.2M.
In the past year, @parahelp_ai has become the go-to AI support agent for the world’s fastest-moving software companies, and we're proud to say that 0% of the companies we've onboarded have churned.
We’re hiring exceptional engineers, so if you’re excited to build on the frontier of applied AI for customer support, please reach out!
Parahelp retweeted
At first, prompting seemed to be a temporary workaround for getting the most out of large language models. But over time, it's become critical to the way we interact with AI.
On the @LightconePod, Garry, Harj, Diana, and Jared break down what they've learned from working with hundreds of founders building with LLMs: why prompting still matters, where it breaks down, and how teams are making it more reliable in production.
They share real examples of prompts that failed, how companies are testing for quality, and what the best teams are doing to make LLM outputs useful and predictable.
0:58 - Parahelp’s prompt example
4:59 - Different types of prompts
6:51 - Metaprompting
7:58 - Using examples
12:10 - Some tricks for longer prompts
14:18 - Findings on evals
17:25 - Every founder has become a forward-deployed engineer (FDE)
23:18 - Vertical AI agents are closing big deals with the FDE model
26:13 - The personalities of the different LLMs
27:26 - Lessons from rubrics
29:47 - Kaizen and the art of communication
Parahelp retweeted
Reviewed the customer support tickets with my team today and was genuinely impressed by the AI support solution from @parahelp_ai. We're not only seeing a significant boost in efficiency, but more importantly, the customer experience has improved dramatically!
Parahelp retweeted
YC S24's @parahelp_ai is an AI support agent for software companies that can resolve support tickets end-to-end. This includes taking relevant actions in tools like Stripe, Retool, and Linear.
Congrats on the launch, @ankerbachryhl and @MadsLunau!
ycombinator.com/launches/LkP…









