Notifications for AI agents and LLM apps

In solo development with AI you do the work as a trio: you, the AI assistant in the IDE and autonomous agents that iterate on things while you switch to another task. This mode has its own set of “blind spots”:

Long-running autonomous tasks — an agent spends half an hour dealing with a DB migration, and you don’t want to check the terminal every 30 seconds.
External dependencies — LLM APIs, vector DBs, embeddings service: their status changes without warning, and you don’t have an SRE team.
Cost — a lot of tokens get burned; it’s easy to lose control of the bill.
Model quality — a new model release can break your pipeline right in the middle of the night.
MCP tools — if your AI calls its MCP server, its outage looks like “the model is acting up”, not like an alert.

Notifly covers all of this in a few lines: heartbeats, active monitors, webhooks and custom cloud functions for synthetic checks send push to your device exactly when you need to intervene.

Where to start

Human-in-the-loop needed — the agent asks a question with “approve / deny” buttons via /ask and waits, while you answer right from the notification. No server of your own: you add an HTTP request to the agent’s code (a Python example is ready).
Long AI agent task completion — copy the agent-run bash wrapper and launch the agent through it: a push arrives when it finishes, successfully or not.
Stuck agent / loop — the agent sends a heartbeat, and if the pings stop, Notifly tells you. One line with a request in the agent’s loop is enough.
LLM provider availability — an active monitor on the provider’s status page or API. No code, the monitor is created in the admin panel.
LLM API spending — count spend in your own code or, with no code, forward the provider’s billing emails to Email Inbox.

Ready-made recipes

Scenario	What it covers
LLM API spending	Exceeded token budget
LLM provider availability	OpenAI/Anthropic/etc. not responding, 5xx, rate limits
Model latency degradation	Sudden “model has slowed down”
Long AI agent task completion	”Agent finished refactoring — go review it”
Stuck agent / loop	Heartbeat protection against silent hangs
Human-in-the-loop needed	Agent paused a task — your approval is required
Vector DB / RAG infrastructure	Qdrant/Pinecone/Weaviate are down
Eval / model quality drop	Regression after changing prompt or model
Safety / prompt injection triggered	Suspicious user input
MCP server health	Own or third-party MCP stopped responding
Custom cloud function integrity check	Server-side “synthetic user” that sends an alert when something breaks

Additional recipes

AI agents

Response quality

RAG and data

Availability and latency

Cost and quotas

GPU, training and models

Security

Development and deploy

Why push, not email

LLM incidents are often short and noisy: 10 minutes of 500s → fixed. Email alerts arrive in batches with delay and drown in email; a push notification to your phone via Notifly is instant, free, and easy to silently dismiss if you see the incident has already resolved itself. And if an important push stays unread, escalation re-sends it to Telegram, SMS or a phone call, while quiet hours keep minor stuff from waking you at night.

All recipes in this section use the same basic stack:

POST /message — ad-hoc alerts from code;
Heartbeat — “agent is alive”;
Active monitors — external HTTP/TCP/TLS checks;
Webhooks — receipt of events from billing/CI;
Email Inbox — alerts from providers that don’t have webhooks;
custom cloud functions on YC — for your own checks.