Agent recovery data evidence gaps: the broken links between failure, fix and proof, and how to describe them

Short answer

Most gaps in agent recovery data are broken links rather than missing records. The failure sits in a bot or phone log, the fix in a help desk ticket, the proof in a billing or payment system, and nothing joins them. The six gaps that matter are: no stored failure event, no customer context, no link from follow-up to failure, no record of who approved the fix, no version of the routing setup, and no confirmed outcome. Each narrows what a review can use; none rules a company out.

Visual briefFull-size diagram
Six rows of ten blocks each show, out of every ten recoveries at a fictional home-services company, how many keep each piece of expected evidence: failure event 8, customer context 6, follow-up link 4, approver 5, routing version 3 and confirmed outcome 5, with the missing blocks outlined in orange.
Illustrative gap analysis for a fictional 380-person home-services company, based on the owner's rough estimates. Figures are invented for this page.

This page is part of the guide to agent recovery data, which follows one failed chat transfer to a verified fix. Its job is a gap analysis: what a review would expect from a history of recoveries, what support archives typically keep, where the chain breaks, and how to describe it in an introduction.

What a recovery review expects to find

A recovery is assessable when a reviewer can rebuild three things for one case: where the task broke, what someone did about it, and how they knew the fix held. Six kinds of evidence carry that.

Expected evidenceWhat it lets a reviewer rebuild
Failure event with a timeThe exact point the task broke, and why
Customer contextWhat the customer asked, so the task is more than its result
Follow-up linkThat the later ticket is the repair of this failure, not another case
Approver of the fixThat the repair was within policy, for example who approved a refund
Routing or configuration versionWhich setup failed, if rules changed around the same time
Confirmed outcomeThat the fix held: a settled refund, no repeat contact, a closing reason

Agent developers want this chain because a failed run without its repair teaches little. Appen's service page, checked October 18, 2026, describes a trajectory analysis service in which experts classify where agents go wrong and write the correct continuation for failed runs. A company's own linked recoveries are the real-world version of that continuation; unlinked ones are two unrelated events.

The pattern below reflects how support stacks are commonly set up, not a survey of companies.

GapWhat archives usually keepWhat is usually missingEffect on assessment
Failure eventBot outcome or call dispositionThe routing event and its target queueThe break point has to be guessed
Customer contextA summary or intent labelWhat the customer actually saidThe task cannot be reconstructed, only its result
Follow-up linkA new ticket on the next contactThe original conversation or case ID on that ticketThe repair cannot be attributed to the failure
ApproverThe refund or credit itselfWho approved it and in what roleNobody can tell whether the fix was within policy
Routing versionThe current routing rulesEarlier rules, edited in placeIt is unclear which configuration failed
Confirmed outcomeTicket status "solved"A repeat-contact check or settled paymentThe fix might not have worked

The failure event is easier to capture than many companies assume. Zendesk's messaging documentation, for example, describes conversation control being passed to an integration or released back to a default state; events like these mark where a handoff stopped. The hardest gap is usually the follow-up link, because it depends on an agent copying an ID across systems at the moment of the repair.

Ten recoveries at a home-services firm (Illustrative)

Illustrative and fictional. A 380-person home-services company books plumbing and heating visits through a website chat assistant that hands urgent cases to a dispatch team. When a handoff fails, dispatch usually calls the customer back the next morning. The introducer asks the head of customer operations a simple question for each kind of evidence: out of every ten recoveries, roughly how many keep it?

EvidenceOwner's estimate, out of 10Why it falls short
Failure event8Phone-line failures after hours are not logged
Customer context6The bot keeps an intent label; full text only since 2023
Follow-up link4Dispatch opens a new job without the chat ID unless reminded
Approver5Goodwill credits over a set amount need a manager, logged only in billing
Routing version3Rota-based routing rules are edited weekly and not versioned
Confirmed outcome5Job completion is recorded; repeat contact is not checked

Read across, the linked core is the four in ten recoveries that carry the chat ID, and within that group the context and outcome are reasonably complete. The routing gap matters less here than it might elsewhere, because dispatch failures are mostly caused by after-hours staffing, not rule changes. That is a useful thing to say plainly. The graphic on this page draws the same six rows as blocks of ten.

Migration and retention: gaps that open over time

Some gaps are not about how a case was handled but about what happened to the records afterwards.

  • Help desk replacement. Ticket history can carry a lot. Zendesk's developer reference explains that every update to a ticket stores an audit with events such as field changes and comments, which is what lets the order of a recovery be rebuilt. When a company changes help desk, ask whether that audit history migrated or only the final ticket state did.
  • Different retention for bot and ticket records. Conversation logs and tickets often live in different tools with different retention settings. If the bot keeps a shorter history than the help desk, older recoveries have a repair but no recorded failure.
  • Restores after an incident. Records rebuilt from backups may lose links or timestamps; ransomware-restored data integrity covers what to ask.

Exceptions in other workflows behave the same way: a freight audit exception is only useful when the original invoice, the dispute and the correction stay linked.

Saying it plainly in the introduction

Instead ofSay
"Every failure is tracked.""Chat handoff failures are logged; after-hours phone failures are not."
"We link everything.""About four in ten recovery jobs carry the original chat ID."
"Fixes are approved.""Credits above the limit need a manager; approvals sit in billing, not the job."
"We know it worked.""Job completion is recorded; repeat contact is not checked."

Give years and shares rather than adjectives, and note who gave each answer. A company that names its gaps reads as more credible than one that claims a complete archive.

Who owns the records, and what stays unknown

Support operations usually owns conversation and ticket history, finance owns refunds and credits, and IT administers the tools. Authority to discuss licensing normally sits with the COO, CFO or CEO. Bot and help desk vendor terms may affect rights, so a review checks them.

The company test does not change with gaps: 50+ full-time employees at peak (contractors excluded), documented operating history, rights to license and an authorized contact. Companies in the U.S., Canada and the EU qualify, as do companies in the UK, Australia, New Zealand, India, Singapore, South Africa, Latin America, the UAE and Saudi Arabia when at least 70% of the data is in English.

Unknown until SourceX reviews it: the real share of linked recoveries, how customer data will be de-identified, and whether any buyer wants this task type. To decide whether a client is worth introducing at all, use the qualification scorecard. What the company would later assemble is listed in the review packet. For the wider ticket archive, see using historical tickets for a support agent, and for step-by-step records generally, agent trajectory data.

Next step

Refer a company. No cap on rewards. Default reward on a company's first qualifying transaction: the greater of $50,000 plus 5% and 15% of Actual Supplier Payout, with no cap; further qualifying transactions first agreed within 12 months of the first Closing pay 15%. Eligibility and payment conditions apply, including the USD 100,000 Minimum Transaction, and a signed Schedule A or addendum can differ. A lead, meeting or signature alone does not trigger payment.

If you can tell a client's owner which links in their recovery chain hold and which break, register as a partner, check who qualifies, and read the program terms before you make the introduction.

  1. Step 1Share your linkSend your personal link to a company you know.
  2. Step 2Company appliesThe company applies itself at /apply.
  3. Step 3Company signs and is paidThe company signs, delivers its data and is paid by SourceX under its agreement.
  4. Step 4You get your rewardthe greater of $50,000 plus 5% and 15% of the actual supplier payout, with no cap. A reward becomes payable after SourceX has paid the referred company under its signed agreement and the payout conditions in the program terms are met, including finance approval and your tax and payment details.

Common questions

If most recoveries lack a link to the original failure, is the archive worthless?

No. The linked subset may still be large enough to matter, and unlinked cases can sometimes be matched later by time and customer under the company's control. The honest step is to state the share that links, not to round it up.

Which gap is easiest for a company to fix going forward?

The follow-up link. Adding a required field for the original conversation or case ID on recovery tickets costs little and improves every case from that day on, although it does nothing for older history.

Should the introducer check how many recoveries link by looking at tickets?

No. The introducer records the owner's estimate and who gave it. Any counting against real tickets happens inside the company, under its agreement with SourceX.

Sources

  1. developer.zendesk.com/documentation/ticketing/reference-guides/tic…
  2. support.zendesk.com/hc/en-us/articles/5514406080538-About-Sunshi…
  3. appen.com/agentic-ai-trajectory-analysis
  4. refer.sourcex.si/terms

Free resources

Know a company with valuable proprietary data?

Become a referral partner, get your link and introduce the company’s CEO (in an owner-run company, usually the owner). Referral partners can join from most countries. We can't work with partners in countries or regions under U.S. sanctions or on U.S. restricted-party lists. The companies you introduce should be based in the U.S., Canada and the EU, or in the UK, Australia, New Zealand, India, Singapore, South Africa, Latin America, the UAE and Saudi Arabia with at least 70% of their data in English.

Refer a company →

I own a business

Explore licensing your company's data directly to SourceX for AI training and evaluation. Start a short assessment; no uploads needed.

Start an assessment