Every FlowSharp release, feature, improvement, and security fix.
October 31, 2026
MCP tools and the Flow Agent now describe fields with the catalogue's own words: the "help next to every field" programme is complete. The Flow Agent answers usage questions with the guide chapters again, and "Create with AI" shows when it ignores event subscriptions proposed by the model.
October 26, 2026
Help next to every field, from Events to task details and KPIs: clear texts in Italian and English with a link to the right section of the guide; the Events page gains a Home button and the external-events wizard explains how to configure inbound webhooks.
October 10, 2026
Faster events under load and reliable exports even at large volumes.
October 9, 2026
Plan features and limits, consistently applied.
October 7, 2026
Assistants can import maps and Solutions.
October 6, 2026
More consistent flow design from agents too.
October 6, 2026
More reliable forced transitions, verifiable event deliveries and failures traceable in history.
October 5, 2026
Create with AI builds the flow before your eyes: the structure first, then the details of each phase.
September 28, 2026
Stronger in the details: a more consistent engine and human fallback, more precise AI diagnostics, a more accessible Designer with events one click away, clearer items and permissions, and tidier What’s New and Solutions.
September 27, 2026
Fourth tester round — validation, contracts and interface: the generated code for a phase with a very long name no longer breaks the save, the Data Schema now rejects rules it cannot keep instead of silently dropping them, the data-conflict message points to the fix that actually works, a change that alters nothing no longer leaves a false trace in the history, a script with the wrong setData() argument fails right away instead of pretending it worked, and automatic tasks finally say what they decided and who carried them out; a case always tells you where it comes from — manual, API, an MCP assistant, the Flow Agent, an event, a sub-process, a scheduled start or sample data — including the Origin card and the history, the "Archive" dialog says what stays, deleting a folder that only holds disabled or archived flows explains what to do, and task-type names are consistent everywhere, with the right verb for a skipped or failed task.
September 27, 2026
Fourth tester round — AI, MCP and documents: converting a manual decision to Jev now carries over the phase's form and warns when the source phase does not evaluate rules on its own; uploads with missing or extra bytes are rejected right away with a clear message, «Item documents → Active» lists real documents only, and inactive uploads can be deleted, by hand or automatically after 7 days, without leaving leftovers behind; starts from external assistants ask a person to confirm, assistant and integration errors distinguish a missing case from a completed one, AI spend is attributed to whoever started the case; AI diagnostics become consistent — the same AI provider in execution, detail, diagnostics, publishing and import, warnings shown the moment you configure, the real cause of an AI failure in the history, and the connection test recorded in the log.
September 26, 2026
Solutions, ready to use: package the maps, flows, connectors and rules of an entire process into a single versioned file — exportable, importable and already readable by AI assistants.
September 24, 2026
Ready to ship: image promotion with stronger guarantees, consistent What’s New in every installation and a Jev conversion that never rewrites halfway.
September 24, 2026
From human to assisted decisions: prepare a Jev decision from a manual task, retain human review for uncertainty and inspect document context before automating.
September 24, 2026
More control over data and decisions: concurrent drafts protect your edits, documents stay consistent with their case, and history makes interventions, waits and events easier to follow.
September 23, 2026
Jev joins the engine: an AI task can now simply decide — classify, estimate > urgency, check whether something essential is missing — with a dedicated, very fast model > that answers with a probability instead of writing text. The rules you already know take > care of the rest.
September 15, 2026
A consolidation release: assistants and integrations see of flows only what their role allows, WIP limits are no longer silently rounded, and configuration errors speak plainly: Webhook task credentials never appear in answers to agents, a badly written WIP limit is flagged while editing and publishing, a script trying to read the Library where it is not supported stops with a message instead of writing empty values; literal Library search, assistant chat usable from the keyboard.
September 8, 2026
Stronger security, simpler everyday work: a hidden risk in automated scripts is closed, confidential data stays protected across events and flow fields, and documents, the Library, the Designer, Kanban and the extension all gain concrete refinements.
September 2, 2026
Document library and text for AI: your organization's reference materials become stable, named assets you can call from flows and let agents read — and FlowSharp now extracts text from PDF and Word files, safely.
September 1, 2026
Documents meet automations: n8n and AI agents can now upload, update and download documents with the API key — all it takes is a URL.
August 31, 2026
Documents join your processes: contracts, reports and attachments are uploaded straight from forms, with versions, preview, quotas and a grace period — on S3-compatible cloud storage governed by FlowSharp.
August 28, 2026
Your installed base gets itself in order: the new Diagnostics finds work stuck on never-configured automations and unblocks it, privacy protections survive copies and versions, and item creation speaks the language of your process instead of JSON.
August 22, 2026
The cycle's final hardening. OAuth errors with the right code, administration of dynamically registered clients with deactivation, traced client metadata diagnostics, automations that reject never-interpolated templates, and an MCP section that calls things by their name — with a state readable by screen readers too.
August 22, 2026
Lists that don't lie and AI assistants with two more tools. Changing page really skips a whole page, totals stay stable while you scroll, search reaches the task calendar, and counts respect your visibility. MCP assistants gain task listing and data updates with the same rules as the APIs, and read-only users are no longer offered impossible actions.
August 21, 2026
Events delivered all the way through and clear answers even in edge cases. The event engine always executes every action of an event, in the right order and without duplicate effects; an overly wide calendar range is rejected with an explicit message, deleting an initiative from the Plan never leaves orphaned elements, and integrations see more while revealing less.
August 21, 2026
Sensitive data protected across all versions, transparent AI Summary. Sensitive-field classification applies to a process's entire version family, history shows what was actually protected, the AI Summary communicates clear states, and integrations get new tools with explicit risk labels.
August 20, 2026
Remote connectors now truly connect with OAuth. The authorization flow introduced in the previous release only partially worked: remote clients could not find the discovery endpoints. Now they can, and the What's New page is easier to read on phones.
August 19, 2026
OAuth-ready MCP connectors, more transparent events. Remote connectors can authorize without keys in URLs, versioning preserves event actions, and telemetry now distinguishes receiving an event from actually applying an effect.
August 17, 2026
A security-focused update. Two-step verification for administrators, secure one-time alert confirmations, stronger and rotatable at-rest encryption, sign-in links and keys kept out of logged URLs, and less sensitive data retained in history.
August 13, 2026
Flows without hidden dead ends, operational recovery under control. The designer blocks processes that cannot reach a final state, automation stalls become visible alerts, cross-install invitations survive retries and crashes, Admins can recover an item through MCP, and the extension downloads preconfigured from Settings.
August 7, 2026
Honest responses, sequences that never stall. Second stabilization wave: concurrent saves have a single winner, activity sequences always resume — even after a crash —, scheduled items start when you actually move them, event rules now work on human phases too, and the n8n contract says the same thing everywhere: UI, snippets and guides. No migrations: a simple upgrade.
August 5, 2026
The engine becomes crash-proof. Seventeen coordinated changes close critical races and crash windows: events that can no longer be lost, outcomes with a single winner, always-recoverable creations, atomic escalations. With one declared breaking change for n8n integrations.
August 1, 2026
Confidential data stays confidential everywhere, and everyone sees only what is theirs. A safeguard is worth as much as its least guarded exit: a field could be hidden on the item's page and appear in the clear in the indicator computed from that very field, and a read-only role could see no flow in its own list yet still learn names and volumes from another screen. Confidentiality now follows the data wherever it is recomputed, visibility is the same from whichever direction you arrive, and connections with external assistants work the way the standard expects.
July 29, 2026
Uploaded logos are visible again, and the rules hold outside the interface too. Uploading a logo really did work — the file was saved — but nobody could see it back: that is why the defect stayed invisible for so long. Alongside come six security fixes, work that no longer sits stuck in a queue, and a long list of rules the product promised without enforcing them outside its own screens.
July 25, 2026
Work assigned to a name that doesn't exist yet no longer disappears in silence. You can still type a person's name as the assignee before you've even created their user — that's normal while you sketch a process — but now the system tells you, instead of leaving that work with no alerts and no reminders.
July 19, 2026
Stronger foundations: organization isolation in the busiest areas is now guaranteed "by construction" by the system itself, with an automatic guard preventing regressions; every sensitive page's permissions are under continuous test. Same app, much more robust underpinnings.
July 18, 2026
Safer and faster: a last loophole toward the internal network closed in integrations, cache cleared on user switch, responsive login even under load and quicker transitions. Plus, the n8n snippets generated by the app now work on the first try.
July 11, 2026
A fixes release, with one structural improvement: the historical cost of an activity no longer changes retroactively if you later edit its configuration. It also hardens the n8n integrations (production send, import, execution tracking) and PDF printing (never again a silently incomplete document). Includes a database migration (a cost snapshot on activities).
July 6, 2026
The Process Map becomes an operational cockpit: time, costs and alerts of your business right on the map — and the Flow Agent can read it.
July 6, 2026
Execution times visible in the item history, always-unique task codes, snappier worker.
July 5, 2026
QA fix batch for n8n and the designer: clearer import, idempotent snippets, connector test aligned with the real contract, a more honest designer on errors.
July 4, 2026
QA fix batch: more robust filters and parameters, more consistent designer, more reliable dashboard, clearer Chrome extension.
July 4, 2026
Consolidation release: anti-duplicate reliability, consistent access control, and clearer WIP.
July 3, 2026
Pasteable, working n8n example nodes — and a handier way to close tasks from n8n: by code instead of by ID.
July 2, 2026
A Flow Template Library and a smoother n8n integration — open the workflow in one click and test webhooks with a guided popup.
June 23, 2026
Consistent start requirements across every channel + shared "when to use a flow" between the built-in Flow Agent and external MCP agents
June 18, 2026
No more blank dashboard, safer n8n form, admin unblock for stuck AI tasks, and flow publishing via MCP
June 9, 2026
Smarter item search in the Flow Agent, consistent errors between REST and MCP, plus interface fixes
June 4, 2026
Delete mistakenly-created items, list-view action parity, opt-in strict trigger
June 2, 2026
Reusable AI Assistants, AI output mode, ROI & What-If report, copy n8n node
May 31, 2026
Flow Agent — start flows by talking in natural language
May 10, 2026
Visual flow progress, related items, activation mode
May 9-10, 2026
n8n Native Bridge, task views, deploy with SSL
May 7-8, 2026
FlowSharp branding, i18n, SuperAdmin, async webhooks
May 2-6, 2026
Version comparison, multi-AI, MCP Server, CI/CD
Apr 18, 2026
Visual designer, AI forms, automation workers