Beth Saunders 🤓 (she/her)

Senior Community Manager at @Amplitude_HQ, data and marketing professional, crafting enthusiast, foodie, traveller, and crazy cat mom.

[Beth Saunders 🤓 (she/her) @SaundersBeth]

(1/2) some photos I took of downtown St. John's! #nlblizzard2020 #stormageddon2020 #snowmaggedon2020 #nlwx #blizzard2020 #snowstorm #nltraffic #YYT #ExploreNL @NatashaFatah @CBCNL @NTVNewsNL @StJohnsTelegram @EddieSheerr @BrianWalshWX

[Spenser Skates @spenserskates]

Next week we're showing how to build self improving products.

We've been running an automated self improvement engine on our website and product that comes up with opportunities based on analytics, session replay, and customer feedback data. We want teach other builders how to do this themselves!

We're hosting @petergyang, Tony Deng from OpenAI, and our own @Jacob__Newman at Amplitude HQ on Wednesday, November 4. They'll demo what they're building with Codex and Amplitude, their workflows, and where humans still need to intervene.

If you're building products with AI, come see it in action and bring your questions.

Wednesday, November 4, 5:30-8:30pm PT. In person in San Francisco at the Amplitude office.

Sign up here: https://t.co/IWEnP9i3jR

[Krista Letz @kristaletz]

Excited to continue to partner with Amplitude, from an early @cursor_ai customer and now @bot / @spacexai. 💙

[Spenser Skates @spenserskates]

Today we're releasing the first instance of self improving products with a customer: @PixAI_Official

Wave found that publishing artwork on PixAI's AI-image generation product was correlated with retention, but most new users never discovered the publish button. Wave suggested prompting users to publish immediately after generating an image. Now, when a user runs out of image generation credits, a tooltip points them to the Missions tab, where they can publish.

Results:
- Mission opens increased 76%
- Publish rate increased 10%
- Day 1 retention increased 3%

We're opening Wave to more teams who want to spend time with it. Let me know if you want to try it for your product!

[Beth Saunders 🤓 (she/her) @SaundersBeth]

I guess I must be using the "Enterprise B!t*hes" plan

[Beth Saunders 🤓 (she/her) @SaundersBeth]

Uhhh, @meetgranola, are you trolling me or something....?

Apparently I was swearing for 25 minutes while our company all hands was going on, at least according to the transcript ⁉️🤔

If this is a bug, it's definitely the weirdest one I've ever seen.

[Chris Tam @chriswtam]

Our CEO: KEEP IT FOLDED IN THE BOARD MEETING

[Carmen DeCouto @CarmenDecouto]

Competitive connect four player? Come find me on the terrace at Lenny and Friend’s Summit @Amplitude_HQ

[Spenser Skates @spenserskates]

Today we're launching Agent Analytics

Every team shipping an AI agent has the same blind spot. Offline evals pass, you ship, and then you have no idea what's happening in production. AI fails silently. Users ask a question and get different answers. They all look 'engaged' in a classic dashboard. You don't know who got a great response and who got a terrible one.

Agent Analytics solves it:
- Every session scored out of the box on task completion, response quality, friction, safety, and negative feedback
- Topic clustering across thousands of conversations, so you know if a failure hits 1 user or 10,000
- Eval agents that watch for regressions, and if you want will file a Linear ticket or the pull request themselves
- Agent quality sits next to product data, so 'payment scheduling fails 31%' becomes 'which renewals did that cost us?'

The Economist got their agent to a 96.9% task success rate and cut weekly failures 84%.

Included on every plan. Free tier included. https://t.co/K5vqrlMLvd

[Beth Saunders 🤓 (she/her) @SaundersBeth]

@CarmenDecouto I've been feeling more frustrated with Claude's output lately VS a few months ago 😬

[Chris Tam @chriswtam]

@Cloudflare just entered AEO and might already have one of the better approaches out there, mostly because of where they sit in the stack. Three things I want from this category, and no vendor has all three.

One, a standardized panel. If I write my prompt set and my competitor writes theirs, were all just grading a test we wrote ourselves. Cloudflare generates the panel and reuses it across every account in a category, which I like more than I expected to.

Even at @Amplitude_HQ, I spent a lot of time creating the best prompts to track, but is it too biased towards our own products and personas?

Two, real prompts instead of plausible ones. Cloudflare infers what a buyer would ask, same as most of us. Profound and Ahrefs license opt-in clickstream instead. That data is contested (desktop, mostly Chrome, disputed volumes, ethically gray?) and I personally think it's just astrology for marketers. The industry desperately needs first party data.

Three, measured instead of inferred. Cloudflare is in the request path, so crawls, 403s, and referrals back get counted, not reconstructed from server logs. Nobody else can copy that.

One and three from Cloudflare. Two from Profound/Ahrefs. Honestly think two matters least of the three for now.

https://t.co/Kb8goUCWGi

[Spenser Skates @spenserskates]

Today we're introducing Wave. A proactive product agent that helps teams build self-improving products.

Every product team runs the same loop. Build, ship, use, learn. AI has made building and shipping extraordinarily fast. Understanding usage and learning still happen by hand.

Wave runs the whole loop:

- Analyzes your Amplitude data for signals across analytics, feedback, session replays, error logs, agent traces, and experiment results
- Surfaces opportunities in the form of full product specs that you or your agents can approve and ship
- Tracks the experiments and outcomes of what you've built so you can start the loop over again

Your product learns what works and gets smarter every cycle: https://t.co/ulbrPjgHed

[Beth Saunders 🤓 (she/her) @SaundersBeth]

@spenserskates @Amplitude_HQ Want!!

[Beth Saunders 🤓 (she/her) @SaundersBeth]

Super excited to head to NYC on June 1st to co-host the @SlackHQ x @Amplitude_HQ: AI at work event for #NYTechWeek! @Techweek_

If you're in NY that week, join us! https://t.co/z9wrmZAa4j

[Spenser Skates @spenserskates]

cutest part of AI week: animated datamonster

[Frank Lee @frankdotlee]

we’ve shipped a bunch of incredible new tools + skills using @Amplitude_HQ's mcp and i wanted to highlight a few killer use cases i’ve been running as a pm/engineer/builder!

/replay-ux-audit + /debug-replay 👀🎥
we added two new session replay tools (list_session_replays and get_session_replay_events) which allows you to more effectively search across your session replays AND provides the agent access to the underlying events and rrweb data.

this allows your agents to query session replays then analyze what’s happening in your replays.

/monitor-ai-quality + /analyze-ai-topics 🤖📊
if you’re using our new agent analytics product, we’ve added mcp tools to query your LLM sessions, spans, conversations, and tagged traces.

this enables your agents to easily browse your agent interactions, synthesize wha the top error categories are or main topics customers are talking to your agents about, then quickly iterate in your ADE/IDE on agent + prompt improvements.

/review-agent-insights 💡
if you’re a heavy amplitude agent user, we’ve added a get_agent_results tool that lets you query all of your amplitude agent previous conversations and the artifacts attached to them.

so if you have a bunch of dashboard and session replay monitors, you can stack workflows on top to triage and fix those issues.

/diagnose-errors 🚨
fun fact: if you’re using autocapture, we track a bunch of rich web vital data like network requests, status codes, logged errors, and error clicks data as different amplitude event types.

so you can automate workflows using an agent to auto-investigate web failures then fix those issues.

get_flags, create_flags, update_flag 👨🏻‍🔬🧪
if you’re using amplitude for feature flagging, you can create, edit, and retrieve your feature flags all directly via MCP instead of having to manually configure in the UI anymore.

we’ve been using this to scale out the number of experiments we’ve been running internally!

give these a try and lmk if there’s other tools or skills we should be adding! 👀

[Beth Saunders 🤓 (she/her) @SaundersBeth]

In SF this week for a Product Adoption off-site with @Amplitude_HQ! Taking advantage of the in-office perks 🍣👀

[Spenser Skates @spenserskates]

Just redesigned our @Amplitude_HQ office after 3 years of putting it off.

We’re kicking off 3 days a week in person with a sushi event today. What a line!

[Claude @claudeai]

Your work tools in Claude are now available on mobile.

Explore Figma designs, create Canva slides, check Amplitude dashboards, all from your phone.

Give it a try: https://t.co/hwPB3zlk0w

[Eric Kim @eric_nakji]

https://t.co/athW8l2W1o

[Spenser Skates @spenserskates]

https://t.co/cFAPMnWi1y

[Frank Lee @frankdotlee]

last night i downed a beer then wrote a /what-would-lenny-do skill that teaches claude how to navigate @lennysan's mcp then help me strategize expert business and product ideas 😂

i was genuinely surprised at how well it worked - it pulled frameworks from lenny's archive, grounded ideas in product context from my @Amplitude_HQ instance, then pressure-tested ideas sitting on our roadmap.

it surfaced a bunch of great strategies (but also terrible ones too 😅) and archive-backed reasoning in its responses.

you can check out and roast some of the results below + check out the skill in the comments!!